# Managed Inference and Agents

Heroku Managed Inference and Agents is a managed service and add-on that provides developer access to AI models and agentic tools through Heroku applications.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Pax8 launches 8os to let IT partners govern AI agents and 8bot as a managed AI co-worker

DevFeed: [Pax8 launches 8os to let IT partners govern AI agents and 8bot as a managed AI co-worker](<https://devfeed.tech/articles/pax8-launches-8os-to-let-it-partners-govern-ai-agents-and-8bot-as-a-managed-ai-co-worker-90068.md>)

Original publisher: [Read original article](<https://siliconangle.com/2026/10/19/pax8-launches-8os-to-let-it-partners-govern-ai-agents-and-8bot-as-a-managed-ai-coworker/>)

Author: Duncan Riley

Published: 2026-10-19T09:00:58Z

Content type: news

Language: en

Sources: [SiliconANGLE](<https://devfeed.tech/sources/siliconangle.md>)

Topics: [shadow AI](<https://devfeed.tech/topics/shadow-ai.md>), [Managed Inference and Agents](<https://devfeed.tech/topics/managed-inference-and-agents.md>), [Heroku AI](<https://devfeed.tech/topics/heroku-ai.md>), [agent to agent communication](<https://devfeed.tech/topics/agent-to-agent-communication.md>)

Tags: [8bot](<https://devfeed.tech/tags/8bot.md>), [8os](<https://devfeed.tech/tags/8os.md>), [account](<https://devfeed.tech/tags/account.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-coworker](<https://devfeed.tech/tags/ai-coworker.md>), [ai-governance](<https://devfeed.tech/tags/ai-governance.md>), [ai-maturity](<https://devfeed.tech/tags/ai-maturity.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [assessment](<https://devfeed.tech/tags/assessment.md>), [aws](<https://devfeed.tech/tags/aws.md>), [aws-marketplace](<https://devfeed.tech/tags/aws-marketplace.md>), [beyond-emea](<https://devfeed.tech/tags/beyond-emea.md>), [business](<https://devfeed.tech/tags/business.md>), [business-software](<https://devfeed.tech/tags/business-software.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [information-technology](<https://devfeed.tech/tags/information-technology.md>), [it](<https://devfeed.tech/tags/it.md>), [launches](<https://devfeed.tech/tags/launches.md>), [libby-mcilhany](<https://devfeed.tech/tags/libby-mcilhany.md>), [managed-intelligence-providers](<https://devfeed.tech/tags/managed-intelligence-providers.md>), [managed-service-providers](<https://devfeed.tech/tags/managed-service-providers.md>), [news](<https://devfeed.tech/tags/news.md>), [pax8](<https://devfeed.tech/tags/pax8.md>), [scott-chasin](<https://devfeed.tech/tags/scott-chasin.md>), [service](<https://devfeed.tech/tags/service.md>), [shadow-ai](<https://devfeed.tech/tags/shadow-ai.md>), [small-business](<https://devfeed.tech/tags/small-business.md>), [smb-ai-pulse](<https://devfeed.tech/tags/smb-ai-pulse.md>), [software](<https://devfeed.tech/tags/software.md>), [technology](<https://devfeed.tech/tags/technology.md>), [the-latest](<https://devfeed.tech/tags/the-latest.md>)

### AI overview

Pax8 launched 8os, a system for IT service providers to govern AI agents used by their small-business customers, alongside 8bot, a managed AI coworker for employees. Partners can set operating rules for each client, keep client context separate, meter usage, and bill through their existing Pax8 accounts. Limited early access begins this week, with general availability planned for early next year.

### Source excerpt

Small business software marketplace Pax8 Inc. today launched 8os, an operating system that lets its information technology service provider partners govern the artificial intelligence agents running inside their customers' businesses. A second product, 8bot, gives those customers' employees a managed AI coworker that partners deploy and supervise through 8os. Pax8 unveiled both at its Beyond [...] The post Pax8 launches 8os to let IT partners govern AI agents and 8bot as a managed AI co-worker appeared first on SiliconANGLE.

## Scuba launches with $34M to help teams and AI agents manage business data

DevFeed: [Scuba launches with $34M to help teams and AI agents manage business data](<https://devfeed.tech/articles/scuba-launches-with-34m-to-help-teams-and-ai-agents-manage-business-data-86441.md>)

Original publisher: [Read original article](<https://siliconangle.com/2026/10/13/scuba-launches-with-34m-to-help-teams-and-ai-agents-manage-business-data/>)

Author: Maria Deutscher

Published: 2026-10-13T22:59:06Z

Content type: news

Language: en

Sources: [SiliconANGLE](<https://devfeed.tech/sources/siliconangle.md>)

Topics: [context-architecture](<https://devfeed.tech/topics/context-architecture.md>), [Managed Inference and Agents](<https://devfeed.tech/topics/managed-inference-and-agents.md>)

Tags: [accel](<https://devfeed.tech/tags/accel.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [data-management](<https://devfeed.tech/tags/data-management.md>), [funding](<https://devfeed.tech/tags/funding.md>), [funding-round](<https://devfeed.tech/tags/funding-round.md>), [homebrew](<https://devfeed.tech/tags/homebrew.md>), [investment](<https://devfeed.tech/tags/investment.md>), [news](<https://devfeed.tech/tags/news.md>), [productivity](<https://devfeed.tech/tags/productivity.md>), [scuba](<https://devfeed.tech/tags/scuba.md>), [startup](<https://devfeed.tech/tags/startup.md>), [the-latest](<https://devfeed.tech/tags/the-latest.md>)

### AI overview

Scuba, a productivity service that organizes work information in shared Collections and makes it available to AI tools through an MCP server, raised $34 million in two funding rounds. The company says its Capture tools gather materials such as notes, correspondence and media, while AI-generated Briefings summarize changes in Collections. Scuba plans to use the funding to expand engineering and go-to-market efforts.

### Source excerpt

Scuba, the developer of an eponymous productivity service, today announced that it has received $34 million in funding. The company raised the capital over two rounds. Accel led the first investment and co-led the second with IVP. The firms were joined by BoxGroup, Conviction, Homebrew and Scribble Ventures. Scuba also boasts a long list of [...] The post Scuba launches with $34M to help teams and AI agents manage business data appeared first on SiliconANGLE.

## Inside Action Gateway in Managed Agents

DevFeed: [Inside Action Gateway in Managed Agents](<https://devfeed.tech/articles/inside-action-gateway-in-managed-agents-86338.md>)

Original publisher: [Read original article](<https://www.digitalocean.com/blog/action-gateway-managed-agents>)

Author: Tyler Gillam

Published: 2026-10-13T17:26:28Z

Content type: article

Language: en

Sources: [DigitalOcean](<https://devfeed.tech/sources/digitalocean.md>)

Topics: [Managed Inference and Agents](<https://devfeed.tech/topics/managed-inference-and-agents.md>), [Model Context Protocol](<https://devfeed.tech/topics/model-context-protocol.md>), [gateway](<https://devfeed.tech/topics/gateway.md>), [Dynamic authorization rules](<https://devfeed.tech/topics/dynamic-authorization-rules.md>), [human in the loop agent](<https://devfeed.tech/topics/human-in-the-loop-agent.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-applications](<https://devfeed.tech/tags/ai-applications.md>), [api](<https://devfeed.tech/tags/api.md>), [applications](<https://devfeed.tech/tags/applications.md>), [coding-agent](<https://devfeed.tech/tags/coding-agent.md>), [credentials](<https://devfeed.tech/tags/credentials.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [environment](<https://devfeed.tech/tags/environment.md>), [execution](<https://devfeed.tech/tags/execution.md>), [gateway](<https://devfeed.tech/tags/gateway.md>), [github](<https://devfeed.tech/tags/github.md>), [github-issue](<https://devfeed.tech/tags/github-issue.md>), [harness](<https://devfeed.tech/tags/harness.md>), [managed](<https://devfeed.tech/tags/managed.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [model-context-protocol](<https://devfeed.tech/tags/model-context-protocol.md>), [permission](<https://devfeed.tech/tags/permission.md>), [policy](<https://devfeed.tech/tags/policy.md>), [request](<https://devfeed.tech/tags/request.md>), [runtime](<https://devfeed.tech/tags/runtime.md>)

### AI overview

This walkthrough explains how Action Gateway handles agents' requests to act on external systems. It distinguishes work inside an agent's environment from API actions, then describes resolving the tool and caller, applying policy, and dispatching authorized calls. Provider credentials remain outside model context, and human approval can be required when appropriate.

### Source excerpt

A coding agent finishes a change and wants to open a GitHub issue with a link to its results. The agent can describe the issue, but creating it belongs to a different system. It needs a tool that can access GitHub, a connection with permission to use the correct account, and a decision on whether this particular agent is allowed to open an issue. If the request needs human approval, the person must be able to see what is being proposed before the call runs. Harness Runtime provides the agent's working environment within DigitalOcean Managed Agents, handling the outward-facing action. The same Gateway can also serve an agent running elsewhere through Model Context Protocol (MCP), a standard interface for connecting AI applications to tools. GitHub, MCP, and other third-party names appear here only to illustrate how the Gateway works and do not indicate any affiliation, sponsorship, or endorsement. This walkthrough traces what happens to a request, including the point where an unreliable provider leaves the outcome uncertain. The principle is straightforward: a model's suggestion to call a tool is a request, not authority. Action Gateway resolves the tool and caller, applies policy to the specific action, and dispatches an authorized call. The system is designed so that provider credentials remain outside model context and model-written code. Managed execution and governed external action are different jobs. The figure abstracts away internal services and does not depict every network hop. Start with the tool boundary Agent work falls into two groups: what happens inside its own environment and what reaches out to other systems. In a coding environment, reading a file, running pytest, or editing a repository happens in the agent's own workspace. Moving those operations to another service separates them from the files and processes they need. Creating a GitHub issue or updating a ticket is different. That call reaches an external API, often with a credential and a chan

## Clueso Raises $10M From Dharana Capital to Build the Agentic Future of Video Creation

DevFeed: [Clueso Raises $10M From Dharana Capital to Build the Agentic Future of Video Creation](<https://devfeed.tech/articles/clueso-raises-10m-from-dharana-capital-to-build-the-agentic-future-of-video-creation-86077.md>)

Original publisher: [Read original article](<https://hackernoon.com/clueso-raises-$10m-from-dharana-capital-to-build-the-agentic-future-of-video-creation?source=rss>)

Author: Ishan Pandey

Published: 2026-10-13T13:16:23Z

Content type: news

Language: en

Sources: [HackerNoon](<https://devfeed.tech/sources/hackernoon.md>)

Topics: [Managed Inference and Agents](<https://devfeed.tech/topics/managed-inference-and-agents.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [AI for customer service automation](<https://devfeed.tech/topics/ai-for-customer-service-automation.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai-and-ml](<https://devfeed.tech/tags/ai-and-ml.md>), [chatgpt](<https://devfeed.tech/tags/chatgpt.md>), [claude](<https://devfeed.tech/tags/claude.md>), [clueso](<https://devfeed.tech/tags/clueso.md>), [dharana-capital](<https://devfeed.tech/tags/dharana-capital.md>), [good-company](<https://devfeed.tech/tags/good-company.md>), [series-a](<https://devfeed.tech/tags/series-a.md>), [software-engineering](<https://devfeed.tech/tags/software-engineering.md>), [startup-funding](<https://devfeed.tech/tags/startup-funding.md>), [video](<https://devfeed.tech/tags/video.md>), [y-combinator](<https://devfeed.tech/tags/y-combinator.md>)

### AI overview

Clueso raised a $10 million Series A led by Dharana Capital to expand its AI video platform. Its agents navigate companies' software to capture footage, write scripts, produce and edit videos, and update them as products and workflows change. The article describes adoption across more than 1,000 companies and plans to expand enterprise sales, editing tools, and integrations.

### Source excerpt

Clueso raised a $10M Series A led by Dharana Capital for AI agents that capture, script, edit and update business videos for 1,000+ companies.

## DigitalOcean Inference Router Enhancements: Performance Tuned Routing, No Rules to Write

DevFeed: [DigitalOcean Inference Router Enhancements: Performance Tuned Routing, No Rules to Write](<https://devfeed.tech/articles/digitalocean-inference-router-enhancements-performance-tuned-routing-no-rules-to-write-86339.md>)

Original publisher: [Read original article](<https://www.digitalocean.com/blog/inference-router-enhancements>)

Author: DigitalOcean

Published: 2026-10-13T13:00:00Z

Content type: release

Language: en

Sources: [DigitalOcean](<https://devfeed.tech/sources/digitalocean.md>)

Topics: [Managed Inference and Agents](<https://devfeed.tech/topics/managed-inference-and-agents.md>), [baseten](<https://devfeed.tech/topics/baseten.md>), [Benchmark](<https://devfeed.tech/topics/benchmark.md>)

Tags: [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [cost](<https://devfeed.tech/tags/cost.md>), [deepseek](<https://devfeed.tech/tags/deepseek.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [frontier-models](<https://devfeed.tech/tags/frontier-models.md>), [glm](<https://devfeed.tech/tags/glm.md>), [inference](<https://devfeed.tech/tags/inference.md>), [openai](<https://devfeed.tech/tags/openai.md>), [product-updates](<https://devfeed.tech/tags/product-updates.md>)

### AI overview

DigitalOcean describes enhancements to its Inference Router, which automatically routes prompts to models suited to each task using public benchmarks. The release says internal testing across software engineering, reasoning, and agentic work found higher accuracy than Claude Opus 5.5 and GPT-6 Astra at about 22% lower cost.

### Source excerpt

Every few weeks, a new model steps up and claims best-in-class at something. The launch chart makes the case, the link makes the rounds, and your team is back to the question nobody has time for: should we switch? The answer takes a week of evals, side-by-side tests and debate, and by the time your team lands on one, the next contender is already on the scoreboard. It's a race you can't win manually. And the launch charts only tell part of the story. They show where a model is strongest, not where it isn't. Today, we're enhancing the DigitalOcean Inference Router so it makes that call for you. No presets to select, no custom routers to build. Send your prompt, set the model to inference-router, and choose a preference if you want one. The router sends each request to the model that performs best for that job, validated by public benchmarks. The right model for the job, automatically Under the hood, inference-router draws on the entire DigitalOcean Model Catalog: frontier models from Anthropic and OpenAI, open source models like Kimi, GLM, and DeepSeek, all one request away. Every new model gets the same test. The ones that measure up are added to the router. And because every request goes to the model that fits the job, you stop paying frontier prices for work a leaner model handles just as well. In our internal testing across software engineering, reasoning and agentic work, Inference Router had higher accuracy than Claude Opus 5.5 and GPT-6 Astra, at about 22% lower cost. With Inference Router, you stop: Re-running evals every time a model launches Rewriting routing rules when the lineup changes Redeploying to swap a model Holding the "should we switch?" meeting The Inference Router Getting Started page on DigitalOcean cloud console shows the benchmarks behind each use case, how the router scores against the best single model, and which models it's choosing between. It updates whenever we add a model or rerun an evaluation. Here is how some of the models behind th

## Introducing DigitalOcean Signals and Simulations: see how your agents and models really behave in production, then test the fix before it ships

DevFeed: [Introducing DigitalOcean Signals and Simulations: see how your agents and models really behave in production, then test the fix before it ships](<https://devfeed.tech/articles/introducing-digitalocean-signals-and-simulations-see-how-your-agents-and-models-really-behave-in-production-then-test-the-fix-before-it-ships-85201.md>)

Original publisher: [Read original article](<https://www.digitalocean.com/blog/introducing-signals-and-simulations>)

Author: DigitalOcean

Published: 2026-10-12T13:05:00Z

Content type: release

Language: en

Sources: [DigitalOcean](<https://devfeed.tech/sources/digitalocean.md>)

Topics: [Managed Inference and Agents](<https://devfeed.tech/topics/managed-inference-and-agents.md>), [ai observability](<https://devfeed.tech/topics/ai-observability.md>), [Test automation](<https://devfeed.tech/topics/test-automation.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [evaluations](<https://devfeed.tech/tags/evaluations.md>), [execution](<https://devfeed.tech/tags/execution.md>), [inference](<https://devfeed.tech/tags/inference.md>), [infrastructure](<https://devfeed.tech/tags/infrastructure.md>), [latency](<https://devfeed.tech/tags/latency.md>), [observability](<https://devfeed.tech/tags/observability.md>), [product-updates](<https://devfeed.tech/tags/product-updates.md>), [production](<https://devfeed.tech/tags/production.md>)

### AI overview

DigitalOcean introduces Signals and Simulations for monitoring and evaluating AI agents. Signals analyzes production traffic to flag potential issues such as frustrated users, failing tools, and infrastructure constraints. Simulations uses realistic, multi-turn scenarios grounded in production traffic to test changes before they reach users.

### Source excerpt

You ship an agent. It mostly works. Then the feedback loop becomes a support ticket: a user got the wrong answer, a tool call looped four times, a refund went out that shouldn't have. Standard observability tells you the system was up and the latency was fine. It can't tell you the agent chose the wrong tool, used stale context, or made a frustrated user give up. And when you do find the problem, writing realistic test cases to validate a fix means hours of digging through traces or inventing scenarios you hope resemble reality. Today we're launching two capabilities, part of DigitalOcean Agent Learning Services, that address both halves of that problem. Signals watches production traffic on DigitalOcean Managed Agents and DigitalOcean Inference Engine, and automatically highlights potential problems: frustrated users, failing tools, infrastructure constraints. Simulations, a new capability of DigitalOcean Evaluations, lets you test a change through realistic multi-turn scenarios, grounded in that same production traffic, on the same harness and tools your agent uses in production, before it reaches a user. Both run natively on the infrastructure you already use to operate models and agents on DigitalOcean, and both feed the same Evaluations grader you already trust. Signals shows you what went wrong, and Simulations lets you test the fix before it ships. DigitalOcean Signals: stop reading transcripts to find out what broke Agent and inference failures often look technically successful. The tool call returned 200; it just returned the wrong region. The conversation completed; the user left annoyed. Signals catches that class of failure at scale by leveraging the infrastructure provided by DigitalOcean Inference Engine, Harness Runtime and Action Gateway. Signals stitches conversation turns into sessions and classifies each one across three dimensions. Interaction signals that track user sentiment (corrections, escalations, users quitting), Execution signals that tra

## CoreWeave targets AI inference bottlenecks with full-stack optimization

DevFeed: [CoreWeave targets AI inference bottlenecks with full-stack optimization](<https://devfeed.tech/articles/coreweave-targets-ai-inference-bottlenecks-with-full-stack-optimization-77535.md>)

Original publisher: [Read original article](<https://siliconangle.com/2026/10/08/ai-inference-gets-full-stack-coreweave-launches-forge-fullyconnected/>)

Author: Jonathan Anthony

Published: 2026-10-09T02:30:18Z

Content type: news

Language: en

Sources: [SiliconANGLE](<https://devfeed.tech/sources/siliconangle.md>)

Topics: [AI Infrastructure](<https://devfeed.tech/topics/ai-infrastructure.md>), [Managed Inference and Agents](<https://devfeed.tech/topics/managed-inference-and-agents.md>), [vllm](<https://devfeed.tech/topics/vllm.md>), [Dynamo-Triton](<https://devfeed.tech/topics/dynamo-triton.md>), [AWS Trainium](<https://devfeed.tech/topics/aws-trainium.md>)

Tags: [accelerated-computing](<https://devfeed.tech/tags/accelerated-computing.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-cloud](<https://devfeed.tech/tags/ai-cloud.md>), [ai-inference](<https://devfeed.tech/tags/ai-inference.md>), [ai-infrastructure](<https://devfeed.tech/tags/ai-infrastructure.md>), [ai-networking](<https://devfeed.tech/tags/ai-networking.md>), [ai-operationalization](<https://devfeed.tech/tags/ai-operationalization.md>), [ai-storage](<https://devfeed.tech/tags/ai-storage.md>), [cloud-computing](<https://devfeed.tech/tags/cloud-computing.md>), [coreweave](<https://devfeed.tech/tags/coreweave.md>), [coreweave-forge](<https://devfeed.tech/tags/coreweave-forge.md>), [cost](<https://devfeed.tech/tags/cost.md>), [cube-event-coverage](<https://devfeed.tech/tags/cube-event-coverage.md>), [data-center-cooling](<https://devfeed.tech/tags/data-center-cooling.md>), [data-centers](<https://devfeed.tech/tags/data-centers.md>), [dave-vellante](<https://devfeed.tech/tags/dave-vellante.md>), [developer](<https://devfeed.tech/tags/developer.md>), [developer-experience](<https://devfeed.tech/tags/developer-experience.md>), [development](<https://devfeed.tech/tags/development.md>), [dynamo](<https://devfeed.tech/tags/dynamo.md>), [forge](<https://devfeed.tech/tags/forge.md>), [fully-connected-2026](<https://devfeed.tech/tags/fully-connected-2026.md>), [fullyconnected](<https://devfeed.tech/tags/fullyconnected.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [gpu-infrastructure](<https://devfeed.tech/tags/gpu-infrastructure.md>), [gpu-utilization](<https://devfeed.tech/tags/gpu-utilization.md>), [john-furrier](<https://devfeed.tech/tags/john-furrier.md>), [managed-services](<https://devfeed.tech/tags/managed-services.md>), [model-training](<https://devfeed.tech/tags/model-training.md>), [models](<https://devfeed.tech/tags/models.md>), [news](<https://devfeed.tech/tags/news.md>), [nvidia](<https://devfeed.tech/tags/nvidia.md>), [observability](<https://devfeed.tech/tags/observability.md>), [optimization](<https://devfeed.tech/tags/optimization.md>), [production-ai](<https://devfeed.tech/tags/production-ai.md>), [software](<https://devfeed.tech/tags/software.md>), [thecube](<https://devfeed.tech/tags/thecube.md>), [urvashi-chowdhary](<https://devfeed.tech/tags/urvashi-chowdhary.md>)

### AI overview

CoreWeave is expanding beyond GPU capacity with managed services for training, post-training, and inference. The article describes layer-by-layer inference optimization using vLLM, quantized models, and custom speculative decoders, and reports that its preview RL Rollouts capability improved model reload latency by 15x in testing. CoreWeave Forge brings serving, observability, post-training, and evaluation together, with a free entry tier and paid tiers offering additional capabilities.

### Source excerpt

AI inference is fast becoming the workload that decides the economics of the AI boom. Training built the first wave of GPU clouds, but serving models faster and cheaper will define the next. That shift is pushing specialized cloud providers beyond raw GPU capacity into storage, networking and software. One provider is layering managed services [...] The post CoreWeave targets AI inference bottlenecks with full-stack optimization appeared first on SiliconANGLE.

## Agents that can pay: building Restock with Stripe's Link and Managed Deep Agents

DevFeed: [Agents that can pay: building Restock with Stripe's Link and Managed Deep Agents](<https://devfeed.tech/articles/agents-that-can-pay-building-restock-with-stripe-s-link-and-managed-deep-agents-78275.md>)

Original publisher: [Read original article](<https://www.langchain.com/blog/agents-that-can-pay-with-stripe-link>)

Author: LangChain Accounts

Published: 2026-10-08T17:37:00Z

Content type: tutorial

Language: en

Sources: [LangChain Blog](<https://devfeed.tech/sources/langchain-blog.md>)

Topics: [IS-IS](<https://devfeed.tech/topics/is-is.md>), [Managed Inference and Agents](<https://devfeed.tech/topics/managed-inference-and-agents.md>), [Slack](<https://devfeed.tech/topics/slack.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [api](<https://devfeed.tech/tags/api.md>), [consent](<https://devfeed.tech/tags/consent.md>), [http](<https://devfeed.tech/tags/http.md>), [human-review](<https://devfeed.tech/tags/human-review.md>), [slack](<https://devfeed.tech/tags/slack.md>), [stripe](<https://devfeed.tech/tags/stripe.md>)

### AI overview

The article walks through Restock, a sample Slack agent that searches for products and places purchases using Stripe Link and the Machine Payments Protocol. It explains the payment flow, spending limits, credential handling, and user approvals, then describes setup options for trying the sample.

### Source excerpt

Build an agent that pays for real purchases. Restock runs in Slack on Managed Deep Agents and pays with Stripe's Link over the Machine Payments Protocol.

## Managed Deep Agents 0.8 adds user-scoped memory, credentials, HTTP channels, and web search

DevFeed: [Managed Deep Agents 0.8 adds user-scoped memory, credentials, HTTP channels, and web search](<https://devfeed.tech/articles/managed-deep-agents-delivers-a-better-user-experience-for-agents-in-production-78332.md>)

Original publisher: [Read original article](<https://www.langchain.com/blog/langsmith-managed-deep-agents-whats-new>)

Author: LangChain Accounts

Published: 2026-10-08T11:05:30Z

Content type: release

Language: en

Sources: [LangChain Blog](<https://devfeed.tech/sources/langchain-blog.md>)

Topics: [Managed Inference and Agents](<https://devfeed.tech/topics/managed-inference-and-agents.md>), [hosted-agents](<https://devfeed.tech/topics/hosted-agents.md>), [human-in-the-loop UX](<https://devfeed.tech/topics/human-in-the-loop-ux.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [agents-in-production](<https://devfeed.tech/tags/agents-in-production.md>), [api](<https://devfeed.tech/tags/api.md>), [production](<https://devfeed.tech/tags/production.md>)

### AI overview

LangChain's Managed Deep Agents 0.8 release adds user-scoped memory and credentials, HTTP channels, Slack file transfer, and built-in web search powered by Parallel. The release targets teams building production agents, with identity and access policies intended to keep shared agent context separate from individual user information.

### Source excerpt

Managed Deep Agents is the simplest way to build, deploy, and run agents in production. The 0.8 release adds support for user-owned credentials, user-level memory, HTTP channels, file transfer in Slack and a pre-built tool for web search.

## What's New in Managed Deep Agents: schedules, per-run configuration, and Slack reactions

DevFeed: [What's New in Managed Deep Agents: schedules, per-run configuration, and Slack reactions](<https://devfeed.tech/articles/what-s-new-in-managed-deep-agents-schedules-per-run-configuration-and-slack-reactions-78337.md>)

Original publisher: [Read original article](<https://www.langchain.com/blog/managed-deep-agents-schedules-per-run-configuration-slack>)

Author: LangChain Accounts

Published: 2026-10-07T18:10:34Z

Content type: release

Language: en

Sources: [LangChain Blog](<https://devfeed.tech/sources/langchain-blog.md>)

Topics: [Managed Inference and Agents](<https://devfeed.tech/topics/managed-inference-and-agents.md>), [LangChain](<https://devfeed.tech/topics/langchain.md>), [Slack](<https://devfeed.tech/topics/slack.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [managed](<https://devfeed.tech/tags/managed.md>), [schedules](<https://devfeed.tech/tags/schedules.md>), [slack](<https://devfeed.tech/tags/slack.md>)

### AI overview

Managed Deep Agents v0.9 adds agent-created reminders and recurring schedules, per-run configuration of models, skills, tools, and sandboxes, and configurable Slack reactions. The post describes how schedules inherit the originating channel and user permissions, while per-run configuration can tailor one deployment to different teams or repositories.

### Source excerpt

LangChain just released new capabilities in Managed Deep Agents. Agents can now schedule follow-ups, reconfigure themselves on every run, and react to Slack messages.

## MasterClass bets AI teaching agents can broaden access to tutoring

DevFeed: [MasterClass bets AI teaching agents can broaden access to tutoring](<https://devfeed.tech/articles/masterclass-bets-ai-teaching-agents-can-broaden-access-to-tutoring-66422.md>)

Original publisher: [Read original article](<https://siliconangle.com/2026/10/06/ai-teaching-agents-masterclass-tackles-tutoring-costs-fullyconnected/>)

Author: Jonathan Anthony

Published: 2026-10-06T18:53:26Z

Content type: news

Language: en

Sources: [SiliconANGLE](<https://devfeed.tech/sources/siliconangle.md>)

Topics: [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [Managed Inference and Agents](<https://devfeed.tech/topics/managed-inference-and-agents.md>), [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [Loop Engineering](<https://devfeed.tech/topics/loop-engineering.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-cloud](<https://devfeed.tech/tags/ai-cloud.md>), [ai-in-education](<https://devfeed.tech/tags/ai-in-education.md>), [ai-inference](<https://devfeed.tech/tags/ai-inference.md>), [ai-teaching-agents](<https://devfeed.tech/tags/ai-teaching-agents.md>), [ai-tutoring](<https://devfeed.tech/tags/ai-tutoring.md>), [cloud-computing](<https://devfeed.tech/tags/cloud-computing.md>), [coreweave](<https://devfeed.tech/tags/coreweave.md>), [cube-event-coverage](<https://devfeed.tech/tags/cube-event-coverage.md>), [dave-vellante](<https://devfeed.tech/tags/dave-vellante.md>), [full-stack](<https://devfeed.tech/tags/full-stack.md>), [fully-connected-2026](<https://devfeed.tech/tags/fully-connected-2026.md>), [fullyconnected](<https://devfeed.tech/tags/fullyconnected.md>), [gpu-utilization](<https://devfeed.tech/tags/gpu-utilization.md>), [john-furrier](<https://devfeed.tech/tags/john-furrier.md>), [lukas-biewald](<https://devfeed.tech/tags/lukas-biewald.md>), [mandar-bapaye](<https://devfeed.tech/tags/mandar-bapaye.md>), [model-context-protocol](<https://devfeed.tech/tags/model-context-protocol.md>), [model-training](<https://devfeed.tech/tags/model-training.md>), [multi-agent-systems](<https://devfeed.tech/tags/multi-agent-systems.md>), [nasdaq-crwv](<https://devfeed.tech/tags/nasdaq-crwv.md>), [news](<https://devfeed.tech/tags/news.md>), [personalized-learning](<https://devfeed.tech/tags/personalized-learning.md>), [thecube](<https://devfeed.tech/tags/thecube.md>), [yanka-industries](<https://devfeed.tech/tags/yanka-industries.md>)

### AI overview

MasterClass is developing a multi-agent teaching system that adapts lessons to learners' engagement, while CoreWeave advises on product development and infrastructure. The article describes iterative evaluation, monitoring agent interactions in production, and an agent that reviews traces nightly to flag issues and likely causes.

### Source excerpt

AI teaching agents could make personalized instruction available to more learners by reducing the cost and staffing demands of one-to-one tutoring. MasterClass is exploring that potential through a system designed to adapt to how each student learns. The shift is also feeding CoreWeave Inc.'s full-stack AI cloud push as companies move AI agents out of [...] The post MasterClass bets AI teaching agents can broaden access to tutoring appeared first on SiliconANGLE.

## What are the differences between Claude Managed agents and Claude Code?

DevFeed: [What are the differences between Claude Managed agents and Claude Code?](<https://devfeed.tech/articles/what-are-the-differences-between-claude-managed-agents-and-claude-code-65385.md>)

Original publisher: [Read original article](<https://www.rogerperkin.co.uk/faq/what-are-the-differences-between-claude-managed-agents-and-claude-code/>)

Author: Roger Perkin

Published: 2026-10-06T08:46:58Z

Content type: comparison

Language: en

Sources: [Roger Perkin Network Automation Consultant](<https://devfeed.tech/sources/roger-perkin-network-automation-consultant.md>)

Topics: [Managed Inference and Agents](<https://devfeed.tech/topics/managed-inference-and-agents.md>), [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [anthropic](<https://devfeed.tech/topics/anthropic.md>)

Tags: [agent-gateway](<https://devfeed.tech/tags/agent-gateway.md>), [agent-infrastructure](<https://devfeed.tech/tags/agent-infrastructure.md>), [agents](<https://devfeed.tech/tags/agents.md>), [api](<https://devfeed.tech/tags/api.md>), [backend](<https://devfeed.tech/tags/backend.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [cloud-infrastructure](<https://devfeed.tech/tags/cloud-infrastructure.md>), [faq](<https://devfeed.tech/tags/faq.md>), [primary](<https://devfeed.tech/tags/primary.md>)

### AI overview

Claude Managed Agents is described as a hosted cloud service for autonomous, long-running background agents, while Claude Code is an interactive coding tool used in a local environment. The document compares their execution models, infrastructure, pricing, and distinguishes the hosted service from OpenClaw, a self-hosted agent gateway.

### Source excerpt

Claude Managed Agents Overview Claude Code is an interactive developer tool for coding, while Claude Managed Agents is a fully hosted cloud infrastructure service that runs autonomous, long-running background agents for you. Core Differences Claude Managed Agents Pricing Claude Managed Agents vs OpenClaw Claude Managed Agents and OpenClaw are distinct approaches to AI agent infrastructure: Claude Managed Agents is a fully ...

## DigitalOcean Managed Agents Brings Managed Cloud Infrastructure to AI Agents

DevFeed: [DigitalOcean Managed Agents Brings Managed Cloud Infrastructure to AI Agents](<https://devfeed.tech/articles/digitalocean-managed-agents-brings-managed-cloud-infrastructure-to-ai-agents-63822.md>)

Original publisher: [Read original article](<https://www.infoq.com/news/2026/10/digitalocean-managed-agents/>)

Author: Sergio De Simone

Published: 2026-10-02T09:00:00Z

Content type: news

Language: en

Sources: [InfoQ](<https://devfeed.tech/sources/infoq.md>)

Topics: [Managed Inference and Agents](<https://devfeed.tech/topics/managed-inference-and-agents.md>), [Digital Ocean](<https://devfeed.tech/topics/digital-ocean.md>), [Docker Sandboxes](<https://devfeed.tech/topics/docker-sandboxes.md>)

Tags: [agent-management](<https://devfeed.tech/tags/agent-management.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-ml-data-engineering](<https://devfeed.tech/tags/ai-ml-data-engineering.md>), [architecture-design](<https://devfeed.tech/tags/architecture-design.md>), [cloud-sandboxes](<https://devfeed.tech/tags/cloud-sandboxes.md>), [cost](<https://devfeed.tech/tags/cost.md>), [development](<https://devfeed.tech/tags/development.md>), [devops](<https://devfeed.tech/tags/devops.md>), [digital-ocean](<https://devfeed.tech/tags/digital-ocean.md>), [digitalocean-managed-agents](<https://devfeed.tech/tags/digitalocean-managed-agents.md>), [large-language-models](<https://devfeed.tech/tags/large-language-models.md>), [microvm](<https://devfeed.tech/tags/microvm.md>), [ml-data-engineering](<https://devfeed.tech/tags/ml-data-engineering.md>), [news](<https://devfeed.tech/tags/news.md>), [orchestration](<https://devfeed.tech/tags/orchestration.md>), [virtual-machines](<https://devfeed.tech/tags/virtual-machines.md>)

### AI overview

DigitalOcean's Managed Agents public preview combines a microVM-based Harness Runtime with an Action Gateway for agent tools and services. It provides persistent, isolated compute sessions, supports parallel agent work, and adds controls such as managed permissions, approval for sensitive actions, rate limiting, retries and timeouts. The article compares it with Docker Cloud Sandboxes, which it describes as more focused on developer workflows, while DigitalOcean's offering emphasizes production infrastructure and orchestration.

### Source excerpt

DigitalOcean recently launched DigitalOcean Managed Agents in public preview, offering a managed cloud infrastructure layer for AI agents with isolated microVM runtimes, governed tool access, and serverless AI inference. By Sergio De Simone

## Introducing Agent Droplets: everything an agent needs, one price, one bill

DevFeed: [Introducing Agent Droplets: everything an agent needs, one price, one bill](<https://devfeed.tech/articles/introducing-agent-droplets-everything-an-agent-needs-one-price-one-bill-63109.md>)

Original publisher: [Read original article](<https://www.digitalocean.com/blog/introducing-agent-droplets>)

Author: DigitalOcean

Published: 2026-10-01T12:05:00Z

Content type: article

Language: en

Sources: [DigitalOcean](<https://devfeed.tech/sources/digitalocean.md>)

Topics: [Managed Inference and Agents](<https://devfeed.tech/topics/managed-inference-and-agents.md>), [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>), [Infrastructure as a Service (IaaS)](<https://devfeed.tech/topics/infrastructure-as-a-service-iaas.md>), [fly.io](<https://devfeed.tech/topics/fly-io.md>), [Claude](<https://devfeed.tech/topics/claude.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [anthropic](<https://devfeed.tech/tags/anthropic.md>), [aws](<https://devfeed.tech/tags/aws.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [cost](<https://devfeed.tech/tags/cost.md>), [fly-io](<https://devfeed.tech/tags/fly-io.md>), [inference](<https://devfeed.tech/tags/inference.md>), [opencode](<https://devfeed.tech/tags/opencode.md>), [product-updates](<https://devfeed.tech/tags/product-updates.md>), [production](<https://devfeed.tech/tags/production.md>), [queries](<https://devfeed.tech/tags/queries.md>), [sandbox](<https://devfeed.tech/tags/sandbox.md>)

### AI overview

DigitalOcean introduces Agent Droplets as a way to simplify how developers pay to run AI agents. The article describes the fragmented costs of combining an agent harness, sandbox, inference, storage, and search across multiple vendors, where separate pricing units and invoices make individual run costs difficult to track. It frames the new offer as an effort to make agent infrastructure pricing more predictable and billing easier to understand.

### Source excerpt

Last week we launched DigitalOcean Managed Agents in public preview: a managed runtime, governed access to more than 16,000 tools, serverless inference, and persistent memory and storage, all on one cloud. Developers have already started thousands of agent sessions. Today we're making the next part simpler: paying for it. Building an agent that does something useful has gotten easy. Running it has not. A production agent needs a harness to drive the loop, a sandbox to execute code safely, inference to think, storage to remember between sessions, and tools to reach the web and other systems. Today, those come from different companies, each billing in its own unit on a separate invoice. Here is one stack a customer described to us: OpenCode Go as the harness, Fly.io for sandboxes, AWS for storage, Fireworks for inference on open models, Anthropic for frontier models, and Parallel for web search. The harness was a flat monthly subscription. Sandbox time was billed per CPU-hour and GB-hour. Inference was per token, at a different rate for every model. Storage was per gigabyte-month plus requests. Search was per thousand queries. Six vendors, six invoices, dozens of pricing units, and a pile of glue code to hold it together. Nobody on the team could say what a single agent run had cost. The offerings that try to combine some of these pieces have a gap in the middle. Sandbox vendors do not run inference. Harness and model vendors do not run sandboxes or storage, and some limit agent workloads on their flat subscriptions. The hyperscalers do run everything, but they meter it as a dozen separate line items with enterprise-grade complexity to match. If you are one developer or a small team, none of these give you the thing you actually want: a price you can predict and a bill you can read. A better way, from the people who brought you the Droplet Fourteen years ago we put a virtual machine on the internet for $5 a month with everything included, and called it a Droplet. A ge

## How to scale agentic applications without creating AI sprawl

DevFeed: [How to scale agentic applications without creating AI sprawl](<https://devfeed.tech/articles/how-to-scale-agentic-applications-without-creating-ai-sprawl-62672.md>)

Original publisher: [Read original article](<https://www.databricks.com/blog/how-scale-agentic-applications-without-creating-ai-sprawl>)

Author: Julia Powell; Sirui Sun

Published: 2026-09-30T16:46:25Z

Content type: article

Language: en

Sources: [Databricks](<https://devfeed.tech/sources/databricks.md>)

Topics: [Managed Inference and Agents](<https://devfeed.tech/topics/managed-inference-and-agents.md>), [databricks](<https://devfeed.tech/topics/databricks.md>)

Tags: [agent-bricks](<https://devfeed.tech/tags/agent-bricks.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [governance](<https://devfeed.tech/tags/governance.md>), [observability](<https://devfeed.tech/tags/observability.md>), [platform](<https://devfeed.tech/tags/platform.md>), [scale](<https://devfeed.tech/tags/scale.md>)

### AI overview

The article describes how enterprises can scale agentic applications while limiting duplicated integrations, fragmented context, inconsistent policies, and rising costs. It presents choice, governed context, and consistent control as key infrastructure needs, and describes Databricks Agent Bricks, Omnigent, and Unity Gateway as a shared platform layer for building and governing agent fleets.

### Source excerpt

Building an agent is getting easier. More capable models and coding agents are making...

## OpenAI Launches dots: Always-On GPT-6 Astra Agents That Work From Their Own Cloud Computers

DevFeed: [OpenAI Launches dots: Always-On GPT-6 Astra Agents That Work From Their Own Cloud Computers](<https://devfeed.tech/articles/openai-launches-dots-always-on-gpt-6-astra-agents-that-work-from-their-own-cloud-computers-62183.md>)

Original publisher: [Read original article](<https://www.marktechpost.com/2026/09/29/openai-launches-dots-always-on-gpt-6-astra-agents-that-work-from-their-own-cloud-computers/>)

Author: Michal Sutter

Published: 2026-09-29T18:30:13Z

Content type: news

Language: en

Sources: [MarkTechPost](<https://devfeed.tech/sources/marktechpost.md>)

Topics: [gpt-6-astra](<https://devfeed.tech/topics/gpt-6-astra.md>), [Managed Inference and Agents](<https://devfeed.tech/topics/managed-inference-and-agents.md>), [codex](<https://devfeed.tech/topics/codex.md>), [Cloud](<https://devfeed.tech/topics/cloud.md>), [agent orchestration](<https://devfeed.tech/topics/agent-orchestration.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>)

Tags: [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-infrastructure](<https://devfeed.tech/tags/ai-infrastructure.md>), [ai-shorts](<https://devfeed.tech/tags/ai-shorts.md>), [applications](<https://devfeed.tech/tags/applications.md>), [apps](<https://devfeed.tech/tags/apps.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [astra](<https://devfeed.tech/tags/astra.md>), [background-work](<https://devfeed.tech/tags/background-work.md>), [beta](<https://devfeed.tech/tags/beta.md>), [browser](<https://devfeed.tech/tags/browser.md>), [business](<https://devfeed.tech/tags/business.md>), [chatgpt](<https://devfeed.tech/tags/chatgpt.md>), [chatgpt-work](<https://devfeed.tech/tags/chatgpt-work.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [dots](<https://devfeed.tech/tags/dots.md>), [editors-pick](<https://devfeed.tech/tags/editors-pick.md>), [for-devs](<https://devfeed.tech/tags/for-devs.md>), [gpt-6](<https://devfeed.tech/tags/gpt-6.md>), [gpt-6-astra](<https://devfeed.tech/tags/gpt-6-astra.md>), [launches](<https://devfeed.tech/tags/launches.md>), [new-releases](<https://devfeed.tech/tags/new-releases.md>), [openai](<https://devfeed.tech/tags/openai.md>), [plugins](<https://devfeed.tech/tags/plugins.md>), [post](<https://devfeed.tech/tags/post.md>), [software-engineering](<https://devfeed.tech/tags/software-engineering.md>), [staff](<https://devfeed.tech/tags/staff.md>), [tech-news](<https://devfeed.tech/tags/tech-news.md>), [technology](<https://devfeed.tech/tags/technology.md>), [uncategorized](<https://devfeed.tech/tags/uncategorized.md>), [work](<https://devfeed.tech/tags/work.md>)

### AI overview

OpenAI introduced dots, persistent GPT-6 Astra agents that run on dedicated cloud computers and browsers. They can work across connected apps and continue in the background, with controls for permissions, review, monitoring, and user oversight. The article describes availability as a managed ChatGPT product for eligible users and workspace plans.

### Source excerpt

OpenAI just introduced dots at their DevDay today. Dots are persistent AI agents powered by GPT-6 Astra. Each dot gets its own cloud computer and browser. It works across 4,000+ apps through ChatGPT plugins and keeps going after you log off. Is it deployable today? Yes, as a managed product. Dots are rolling out in [...] The post OpenAI Launches dots: Always-On GPT-6 Astra Agents That Work From Their Own Cloud Computers appeared first on MarkTechPost.

## Naive Managed Agents reports lower costs on long-horizon agent tasks

DevFeed: [Naive Managed Agents reports lower costs on long-horizon agent tasks](<https://devfeed.tech/articles/naive-managed-agents-the-most-efficient-managed-agent-for-long-horizon-tasks-84801.md>)

Original publisher: [Read original article](<https://usenaive.ai/blogs/introducing-naive-managed-agents>)

Author: Naïve

Published: 2026-08-17T00:00:00Z

Content type: article

Language: en

Sources: [Naïve](<https://devfeed.tech/sources/naive.md>)

Topics: [Managed Inference and Agents](<https://devfeed.tech/topics/managed-inference-and-agents.md>), [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>), [hosting](<https://devfeed.tech/topics/hosting.md>), [least privilege](<https://devfeed.tech/topics/least-privilege.md>), [long-running](<https://devfeed.tech/topics/long-running.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [credentials](<https://devfeed.tech/tags/credentials.md>), [harness](<https://devfeed.tech/tags/harness.md>), [launch](<https://devfeed.tech/tags/launch.md>), [managed](<https://devfeed.tech/tags/managed.md>)

### AI overview

Naive introduces Managed Agents, a service designed to run autonomous tasks lasting hours. The article attributes lower operating costs to its model-call pricing, serverless runtime, isolated sandboxes, budgets, and identity features. It reports that, on Long Horizon Terminal Bench with the model held fixed, the service cost $0.2232 per attempted task versus $0.5995 for Claude Code at the same latency, with a higher resolve rate.

### Source excerpt

Same model, same tasks, only the stack changed: Naive Managed Agents finishes a task 2.7x cheaper than the next-best harness while completing more of them. We built every layer of the stack to make that number possible.

## Expanding Managed Agents in Gemini API: background tasks, remote MCP and more

DevFeed: [Expanding Managed Agents in Gemini API: background tasks, remote MCP and more](<https://devfeed.tech/articles/expanding-managed-agents-in-gemini-api-background-tasks-remote-mcp-and-more-89330.md>)

Original publisher: [Read original article](<https://blog.google/innovation-and-ai/technology/developers-tools/expanding-managed-agents-gemini-api/>)

Author: Mariano Cocirio

Published: 2026-07-07T08:54:00Z

Content type: release

Language: en

Sources: [Developer tools](<https://devfeed.tech/sources/developer-tools.md>)

Topics: [Managed Inference and Agents](<https://devfeed.tech/topics/managed-inference-and-agents.md>), [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [long-running](<https://devfeed.tech/topics/long-running.md>)

Tags: [access-tokens](<https://devfeed.tech/tags/access-tokens.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [api](<https://devfeed.tech/tags/api.md>), [background](<https://devfeed.tech/tags/background.md>), [blocking](<https://devfeed.tech/tags/blocking.md>), [developer-tools](<https://devfeed.tech/tags/developer-tools.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [none](<https://devfeed.tech/tags/none.md>)

### AI overview

Google announces Managed Agents capabilities in the Gemini API, including asynchronous background execution, direct connections to remote MCP servers, custom function calling alongside sandbox tools, and credential refresh across interactions.

### Source excerpt

Managed agents feature bundle launch

## Role-Based Access Control for humans and agents

DevFeed: [Role-Based Access Control for humans and agents](<https://devfeed.tech/articles/role-based-access-control-for-humans-and-agents-79933.md>)

Original publisher: [Read original article](<https://modal.com/blog/role-based-access-control-for-humans-and-agents>)

Author: Can Duruk; Kareem Sabri

Published: 2026-05-27T00:00:00Z

Content type: release

Language: en

Sources: [Modal](<https://devfeed.tech/sources/modal.md>)

Topics: [rbac](<https://devfeed.tech/topics/rbac.md>), [Access Control](<https://devfeed.tech/topics/access-control.md>), [Managed Inference and Agents](<https://devfeed.tech/topics/managed-inference-and-agents.md>)

Tags: [access-control](<https://devfeed.tech/tags/access-control.md>), [agentic-development](<https://devfeed.tech/tags/agentic-development.md>), [agents](<https://devfeed.tech/tags/agents.md>), [infrastructure](<https://devfeed.tech/tags/infrastructure.md>), [role-based-access-control](<https://devfeed.tech/tags/role-based-access-control.md>)

### AI overview

Modal is making role-based access control available to Team and Enterprise users. Its Restricted Environments limit which users and agents can deploy and manage applications, access logs and secrets, and look up resources across environments. Modal says the permissions architecture is intended to support agentic development, with per-agent limits and resource-based permissions on its roadmap.

### Source excerpt

Introducing Role-Based Access Control for humans and agents, now available for all users on Teams and Enterprise plans.

## Whats New in Heroku AI: New Models and a Flexible Standard Plan

DevFeed: [Whats New in Heroku AI: New Models and a Flexible Standard Plan](<https://devfeed.tech/articles/whats-new-in-heroku-ai-new-models-and-a-flexible-standard-plan-26473.md>)

Original publisher: [Read original article](<https://www.heroku.com/blog/new-models-and-flexible-standard-plan/>)

Author: Anush DSouza

Published: 2026-02-19T17:08:20Z

Content type: release

Language: en

Sources: [Heroku](<https://devfeed.tech/sources/heroku.md>)

Topics: [Managed Inference and Agents](<https://devfeed.tech/topics/managed-inference-and-agents.md>), [Heroku AI](<https://devfeed.tech/topics/heroku-ai.md>), [Heroku](<https://devfeed.tech/topics/heroku.md>), [Claude](<https://devfeed.tech/topics/claude.md>), [Cohere API for embeddings](<https://devfeed.tech/topics/cohere-api-for-embeddings.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [developer](<https://devfeed.tech/tags/developer.md>), [developers](<https://devfeed.tech/tags/developers.md>), [flexibility](<https://devfeed.tech/tags/flexibility.md>), [heroku](<https://devfeed.tech/tags/heroku.md>), [heroku-ai](<https://devfeed.tech/tags/heroku-ai.md>), [inference](<https://devfeed.tech/tags/inference.md>), [managed](<https://devfeed.tech/tags/managed.md>), [managed-inference-and-agents](<https://devfeed.tech/tags/managed-inference-and-agents.md>), [model](<https://devfeed.tech/tags/model.md>), [models](<https://devfeed.tech/tags/models.md>), [news](<https://devfeed.tech/tags/news.md>), [operational](<https://devfeed.tech/tags/operational.md>), [overhead](<https://devfeed.tech/tags/overhead.md>), [plan](<https://devfeed.tech/tags/plan.md>), [standard](<https://devfeed.tech/tags/standard.md>), [updates](<https://devfeed.tech/tags/updates.md>), [whats-new](<https://devfeed.tech/tags/whats-new.md>), [workflows](<https://devfeed.tech/tags/workflows.md>)

### AI overview

Heroku's new standard plan for Managed Inference and Agents lets developers use one add-on and API key across its supported model catalog. Switching models now requires changing the model name in code instead of provisioning another add-on and managing extra config variables. The catalog adds Claude Opus 4.6 and Sonnet 4.6, plus five open-weight models: DeepSeek v3.2, Kimi K2.5, MiniMax M2.1, ZAI GLM 4.7, and GLM 4.7 Flash. The excerpt also announces Cohere Embed V4 for vector search and retrieval, but cuts off before providing further details.

### Source excerpt

Heroku is introducing significant updates to Managed Inference and Agents. These changes focus on reducing developer friction, expanding model catalogue, and streamlining deployment workflows. More flexibility with the new standard plan Until now, Heroku's model-based plans required developers to provision a specific add-on for a specific model. This created significant operational overhead. If you wanted [...] The post Whats New in Heroku AI: New Models and a Flexible Standard Plan appeared first on Heroku.

## Building AI-Powered Observability with Heroku Managed Inference and Agents

DevFeed: [Building AI-Powered Observability with Heroku Managed Inference and Agents](<https://devfeed.tech/articles/building-ai-powered-observability-with-heroku-managed-inference-and-agents-26381.md>)

Original publisher: [Read original article](<https://www.heroku.com/blog/building-ai-powered-observability-with-managed-inference-and-agents/>)

Author: Karunasri (Karuna) Garigipati

Published: 2026-02-13T19:36:30Z

Content type: tutorial

Language: en

Sources: [Heroku](<https://devfeed.tech/sources/heroku.md>)

Topics: [Managed Inference and Agents](<https://devfeed.tech/topics/managed-inference-and-agents.md>), [observability](<https://devfeed.tech/topics/observability.md>), [Heroku](<https://devfeed.tech/topics/heroku.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-coding-assistant](<https://devfeed.tech/tags/ai-coding-assistant.md>), [ai-coding-assistants](<https://devfeed.tech/tags/ai-coding-assistants.md>), [ai-powered](<https://devfeed.tech/tags/ai-powered.md>), [api](<https://devfeed.tech/tags/api.md>), [automatically](<https://devfeed.tech/tags/automatically.md>), [call](<https://devfeed.tech/tags/call.md>), [configure](<https://devfeed.tech/tags/configure.md>), [credentials](<https://devfeed.tech/tags/credentials.md>), [developer-tools](<https://devfeed.tech/tags/developer-tools.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [heroku](<https://devfeed.tech/tags/heroku.md>), [ide](<https://devfeed.tech/tags/ide.md>), [incident](<https://devfeed.tech/tags/incident.md>), [inference](<https://devfeed.tech/tags/inference.md>), [managed](<https://devfeed.tech/tags/managed.md>), [managed-inference-and-agents](<https://devfeed.tech/tags/managed-inference-and-agents.md>), [mcp-on-heroku](<https://devfeed.tech/tags/mcp-on-heroku.md>), [observability](<https://devfeed.tech/tags/observability.md>), [production](<https://devfeed.tech/tags/production.md>), [sentry](<https://devfeed.tech/tags/sentry.md>), [splunk](<https://devfeed.tech/tags/splunk.md>)

### AI overview

The described pattern connects an IDE assistant to Splunk, Honeycomb, and Sentry through MCP tools, with Heroku Managed Inference and Agents handling transport. Each platform gets a consistent callable interface, while tool handlers translate requests into platform-specific API calls; the same approach can expose other APIs as MCP tools. Engineers can ask plain-English questions about production telemetry from their IDE, and the article says the assistant can correlate findings across platforms, including tracing error spikes to regions, subnets, or services. The excerpt mentions deployment with credentials in config vars and a single token for team IDE setup, but omits the specific deployment steps and further details.

### Source excerpt

If you've ever debugged a production incident, you know the drill: IDE on one screen, Splunk on another, Sentry open in a third tab, frantically copying error messages between windows while your PagerDuty keeps buzzing. You ask "What errors spiked in the last hour?" but instead of an answer, you have to context-switch, recall complex [...] The post Building AI-Powered Observability with Heroku Managed Inference and Agents appeared first on Heroku.

## Building AI Search on Heroku

DevFeed: [Building AI Search on Heroku](<https://devfeed.tech/articles/building-ai-search-on-heroku-26382.md>)

Original publisher: [Read original article](<https://www.heroku.com/blog/building-ai-search-on-heroku/>)

Author: Anush DSouza

Published: 2026-01-29T17:50:08Z

Content type: tutorial

Language: en

Sources: [Heroku](<https://devfeed.tech/sources/heroku.md>)

Topics: [AI-driven information retrieval](<https://devfeed.tech/topics/ai-driven-information-retrieval.md>), [Vectors & LLMs](<https://devfeed.tech/topics/vectors-llms.md>), [search-engines](<https://devfeed.tech/topics/search-engines.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [Heroku AI](<https://devfeed.tech/topics/heroku-ai.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [Managed Inference and Agents](<https://devfeed.tech/topics/managed-inference-and-agents.md>), [cosine similarity search](<https://devfeed.tech/topics/cosine-similarity-search.md>), [Enhancing AI model performance](<https://devfeed.tech/topics/enhancing-ai-model-performance.md>), [Heroku](<https://devfeed.tech/topics/heroku.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-search](<https://devfeed.tech/tags/ai-search.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [heroku](<https://devfeed.tech/tags/heroku.md>), [heroku-ai](<https://devfeed.tech/tags/heroku-ai.md>), [managed-inference-and-agents](<https://devfeed.tech/tags/managed-inference-and-agents.md>), [news](<https://devfeed.tech/tags/news.md>), [rag](<https://devfeed.tech/tags/rag.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [vector-search](<https://devfeed.tech/tags/vector-search.md>)

### AI overview

The Heroku AI Search reference app addresses a weakness of vector search: semantic similarity does not guarantee that a document answers the query. Its pipeline crawls URLs, filters site content with a heuristic, splits documents into 1,000-character chunks with 200-character overlap at paragraph or sentence boundaries, embeds them, and stores them in pgvector. At query time, it retrieves the top 20 chunks by cosine similarity, then uses a cross-encoder reranker to score each candidate against the query before Claude generates an answer. The excerpt says reranking can be optional when latency matters more than precision; it does not provide the crawler heuristic or further implementation details.

### Source excerpt

If you've built a RAG (Retrieval Augmented Generation) system, you've probably hit this wall: your vector search returns 20 documents that are semantically similar to the query, but half of them don't actually answer it. A user asks "how do I handle authentication errors?" and gets back documentation about authentication, errors, and error handling in [...] The post Building AI Search on Heroku appeared first on Heroku.

## Optimize Search Precision with Reranking on Heroku AI

DevFeed: [Optimize Search Precision with Reranking on Heroku AI](<https://devfeed.tech/articles/optimize-search-precision-with-reranking-on-heroku-ai-26479.md>)

Original publisher: [Read original article](<https://www.heroku.com/blog/optimize-search-precision-reranking-heroku-ai/>)

Author: Anush DSouza

Published: 2026-01-15T16:00:48Z

Content type: release

Language: en

Sources: [Heroku](<https://devfeed.tech/sources/heroku.md>)

Topics: [Heroku AI](<https://devfeed.tech/topics/heroku-ai.md>), [Managed Inference and Agents](<https://devfeed.tech/topics/managed-inference-and-agents.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [Heroku](<https://devfeed.tech/topics/heroku.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [amazon](<https://devfeed.tech/tags/amazon.md>), [availability](<https://devfeed.tech/tags/availability.md>), [cohere](<https://devfeed.tech/tags/cohere.md>), [general-availability](<https://devfeed.tech/tags/general-availability.md>), [heroku](<https://devfeed.tech/tags/heroku.md>), [heroku-ai](<https://devfeed.tech/tags/heroku-ai.md>), [inference](<https://devfeed.tech/tags/inference.md>), [managed](<https://devfeed.tech/tags/managed.md>), [managed-inference-and-agents](<https://devfeed.tech/tags/managed-inference-and-agents.md>), [models](<https://devfeed.tech/tags/models.md>), [news](<https://devfeed.tech/tags/news.md>), [query](<https://devfeed.tech/tags/query.md>), [relevance](<https://devfeed.tech/tags/relevance.md>), [reranking](<https://devfeed.tech/tags/reranking.md>), [score](<https://devfeed.tech/tags/score.md>), [search](<https://devfeed.tech/tags/search.md>), [semantic](<https://devfeed.tech/tags/semantic.md>), [vector-similarity](<https://devfeed.tech/tags/vector-similarity.md>)

### AI overview

Heroku Managed Inference and Agents now offers Cohere Rerank 3.5 and Amazon Rerank 1.0 for semantic reranking in retrieval-augmented generation pipelines. The excerpt describes a two-stage workflow: retrieve candidate documents, then send them to the Heroku Rerank API to score relevance to a query. Results include each document's original input position and a normalized score, with higher scores indicating better alignment; teams can apply relevance thresholds or limit returned results with a top-N parameter to keep context focused and reduce inference costs. The API is designed for Cohere-format compatibility, and both models are available in US and EU regions. Stated limits and prices differ: Cohere supports up to 250 requests per minute at $2 per 1,000 queries; Amazon supports up to 200 requests per minute at $1 per 1,000 queries.

### Source excerpt

Today, we are announcing the general availability of reranking models on Heroku Managed Inference and Agents, featuring support for Cohere Rerank 3.5 and Amazon Rerank 1.0. Semantic reranking models score documents based on their relevance to a specific query. Unlike keyword search or vector similarity, rerank models understand nuanced semantic relationships to identify the most [...] The post Optimize Search Precision with Reranking on Heroku AI appeared first on Heroku.

## Heroku AI: Accelerating AI Development With New Models, Performance Improvements, and Messages API

DevFeed: [Heroku AI: Accelerating AI Development With New Models, Performance Improvements, and Messages API](<https://devfeed.tech/articles/heroku-ai-accelerating-ai-development-with-new-models-performance-improvements-and-messages-api-26362.md>)

Original publisher: [Read original article](<https://www.heroku.com/blog/accelerating-ai-dev-new-models-performance-improvements-messages-api/>)

Author: Anush DSouza

Published: 2025-12-18T19:42:30Z

Content type: release

Language: en

Sources: [Heroku](<https://devfeed.tech/sources/heroku.md>)

Topics: [Heroku AI](<https://devfeed.tech/topics/heroku-ai.md>), [Managed Inference and Agents](<https://devfeed.tech/topics/managed-inference-and-agents.md>), [Claude](<https://devfeed.tech/topics/claude.md>), [Heroku](<https://devfeed.tech/topics/heroku.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-development](<https://devfeed.tech/tags/ai-development.md>), [ai-models](<https://devfeed.tech/tags/ai-models.md>), [api](<https://devfeed.tech/tags/api.md>), [catalog](<https://devfeed.tech/tags/catalog.md>), [claude](<https://devfeed.tech/tags/claude.md>), [claude-opus](<https://devfeed.tech/tags/claude-opus.md>), [framework](<https://devfeed.tech/tags/framework.md>), [heroku](<https://devfeed.tech/tags/heroku.md>), [heroku-ai](<https://devfeed.tech/tags/heroku-ai.md>), [inference](<https://devfeed.tech/tags/inference.md>), [kimi](<https://devfeed.tech/tags/kimi.md>), [managed](<https://devfeed.tech/tags/managed.md>), [managed-inference-and-agents](<https://devfeed.tech/tags/managed-inference-and-agents.md>), [messages](<https://devfeed.tech/tags/messages.md>), [minimax](<https://devfeed.tech/tags/minimax.md>), [model](<https://devfeed.tech/tags/model.md>), [models](<https://devfeed.tech/tags/models.md>), [news](<https://devfeed.tech/tags/news.md>), [performance](<https://devfeed.tech/tags/performance.md>)

### AI overview

Heroku Managed Inference and Agents adds proprietary models including Claude Opus 4.5 and Amazon Nova 2 Lite, plus open-weight models Kimi K2 Thinking, MiniMax M2, and Qwen3 variants. The full Claude 4.5 family is available in US and EU regions; Claude 3 models are scheduled for depreciation in January 2026. The announcement describes Opus for complex reasoning and planning, Sonnet for enterprise workloads, coding, and analysis, and Haiku for low-latency, high-volume tasks. Heroku also offers preview support for Anthropic's Messages API, an alternative to chatCompletions that aligns with Claude SDKs and enables integration with Claude Code and the Claude Agents SDK. Heroku says open-weight models run on secure AWS compute, and neither Heroku nor the model provider can access the data or use it for training. The excerpt ends before the technical implementation and authentication details.

### Source excerpt

This month marks significant expansion for Heroku Managed Inference and Agents, directly accelerating our AI PaaS framework. We're announcing a substantial addition to our model catalog, providing access to leading proprietary AI models such as Claude Opus 4.5, Nova 2, and open-weight models such as Kimi K2 thinking, MiniMax M2, and Qwen3. These resources are [...] The post Heroku AI: Accelerating AI Development With New Models, Performance Improvements, and Messages API appeared first on Heroku.

[Next page](<https://devfeed.tech/topics/managed-inference-and-agents.md?cursor=WyIyMDI1LTEyLTE4VDE5OjQyOjMwKzAwOjAwIiwgIjI3NjY4NzEyLTRhMWUtNGFhMS1iOTE1LTg4ZGM5MDYzNGY4ZSJd>)