# Honeycomb Blog

Latest blog posts from Honeycomb.

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

## Is Your Observability Stack Just Monitoring in Disguise?

DevFeed: [Is Your Observability Stack Just Monitoring in Disguise?](<https://devfeed.tech/articles/is-your-observability-stack-just-monitoring-in-disguise-126490.md>)

Original publisher: [Read original article](<https://www.honeycomb.io/blog/rick-clark-o11ywashing>)

Author: Rox Williams

Published: 2026-11-10T14:11:17Z

Content type: article

Language: en

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

Topics: [observability](<https://devfeed.tech/topics/observability.md>), [Monitoring](<https://devfeed.tech/topics/monitoring.md>), [dashboards](<https://devfeed.tech/topics/dashboards.md>)

Tags: [budget](<https://devfeed.tech/tags/budget.md>), [build-vs-buy](<https://devfeed.tech/tags/build-vs-buy.md>), [business](<https://devfeed.tech/tags/business.md>), [cardinality](<https://devfeed.tech/tags/cardinality.md>), [charity-majors](<https://devfeed.tech/tags/charity-majors.md>), [context](<https://devfeed.tech/tags/context.md>), [costs](<https://devfeed.tech/tags/costs.md>), [cto](<https://devfeed.tech/tags/cto.md>), [customer](<https://devfeed.tech/tags/customer.md>), [dashboards](<https://devfeed.tech/tags/dashboards.md>), [interview](<https://devfeed.tech/tags/interview.md>), [linux](<https://devfeed.tech/tags/linux.md>), [linux-security](<https://devfeed.tech/tags/linux-security.md>), [monitoring](<https://devfeed.tech/tags/monitoring.md>), [monitoring-tools](<https://devfeed.tech/tags/monitoring-tools.md>), [observability](<https://devfeed.tech/tags/observability.md>), [observability-engineering](<https://devfeed.tech/tags/observability-engineering.md>), [observability-stack](<https://devfeed.tech/tags/observability-stack.md>), [pricing](<https://devfeed.tech/tags/pricing.md>), [requirements](<https://devfeed.tech/tags/requirements.md>), [software-engineering](<https://devfeed.tech/tags/software-engineering.md>)

### AI overview

Rick Clark's key test for distinguishing observability from monitoring is whether you can ask an unplanned question. If you must predict what will break before querying the system, the excerpt says that is monitoring. The conversation also frames observability's value in business outcomes, such as reduced support costs and customer calls, beyond budget alone. It describes "o11ywashing" as vendors relabeling monitoring tools while omitting capabilities such as high-cardinality context, visualizations beyond dashboards, and event-based pricing. The excerpt mentions five tests but explains only the arbitrary-question test, so it does not support a full account of the framework.

### Source excerpt

Charity Majors sits down with Rick Clark for episode three of Leading With Observability to talk o11ywashing: when vendors rename monitoring tools as observability.

## Three LLM Cost Optimization Patterns That Cut Token Spend Without Degrading Quality

DevFeed: [Three LLM Cost Optimization Patterns That Cut Token Spend Without Degrading Quality](<https://devfeed.tech/articles/three-llm-cost-optimization-patterns-that-cut-token-spend-without-degrading-quality-129312.md>)

Original publisher: [Read original article](<https://www.honeycomb.io/blog/llm-cost-optimization-patterns>)

Author: Dan Juengst

Published: 2026-11-05T16:00:00Z

Content type: article

Language: en

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

Topics: [LLM observability](<https://devfeed.tech/topics/llm-observability.md>), [LLM optimization](<https://devfeed.tech/topics/llm-optimization.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>)

Tags: [ai-llms](<https://devfeed.tech/tags/ai-llms.md>), [cloud-costs](<https://devfeed.tech/tags/cloud-costs.md>), [context](<https://devfeed.tech/tags/context.md>), [cost](<https://devfeed.tech/tags/cost.md>), [cost-optimization](<https://devfeed.tech/tags/cost-optimization.md>), [llm](<https://devfeed.tech/tags/llm.md>), [llm-cost-optimization](<https://devfeed.tech/tags/llm-cost-optimization.md>), [observability](<https://devfeed.tech/tags/observability.md>), [optimization](<https://devfeed.tech/tags/optimization.md>), [patterns](<https://devfeed.tech/tags/patterns.md>), [quality](<https://devfeed.tech/tags/quality.md>), [retry](<https://devfeed.tech/tags/retry.md>), [token](<https://devfeed.tech/tags/token.md>)

### AI overview

LLM token costs can be reduced without harming results by targeting waste visible in production traces: repeated context, calls that retry or loop without progress, and output that adds no measurable benefit. Traces link token use to workflow steps, prompt versions, models, retries, tenants, and outcomes, helping teams compare expensive and normal cohorts. Possible fixes include filtering irrelevant retrieval results, summarizing older history, setting retry limits, improving error handling, tightening loop termination, and tailoring output to what the task or next step needs. Make one targeted change at a time and compare cost per successful outcome alongside quality and reliability signals such as completion, acceptance, tool success, parsing, latency, and recovery. Broad prompt shortening, cheaper model routing, or output limits can degrade some workflows, and retries may protect quality when they recover from transient failures.

### Source excerpt

Learn how observability reveals redundant context, retry storms, and overlong outputs so teams can cut LLM token spend without sacrificing quality.

## Good Agents Need Good Managers: What We Heard at Innovation Week

DevFeed: [Good Agents Need Good Managers: What We Heard at Innovation Week](<https://devfeed.tech/articles/good-agents-need-good-managers-what-we-heard-at-innovation-week-118971.md>)

Original publisher: [Read original article](<https://www.honeycomb.io/blog/good-agents-need-good-managers-innovation-week>)

Author: Dormain Drewitz

Published: 2026-11-04T19:00:00Z

Content type: news

Language: en

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

Topics: [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [Loop Engineering](<https://devfeed.tech/topics/loop-engineering.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [OpenTelemetry](<https://devfeed.tech/topics/opentelemetry.md>), [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>)

Tags: [accountability](<https://devfeed.tech/tags/accountability.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-llms](<https://devfeed.tech/tags/ai-llms.md>), [alert](<https://devfeed.tech/tags/alert.md>), [anthropic](<https://devfeed.tech/tags/anthropic.md>), [autonomy](<https://devfeed.tech/tags/autonomy.md>), [aws](<https://devfeed.tech/tags/aws.md>), [billing](<https://devfeed.tech/tags/billing.md>), [budget](<https://devfeed.tech/tags/budget.md>), [bug](<https://devfeed.tech/tags/bug.md>), [cncf](<https://devfeed.tech/tags/cncf.md>), [component](<https://devfeed.tech/tags/component.md>), [context](<https://devfeed.tech/tags/context.md>), [conversion](<https://devfeed.tech/tags/conversion.md>), [cost](<https://devfeed.tech/tags/cost.md>), [culture](<https://devfeed.tech/tags/culture.md>), [documentation](<https://devfeed.tech/tags/documentation.md>), [fleet](<https://devfeed.tech/tags/fleet.md>), [innovation-week](<https://devfeed.tech/tags/innovation-week.md>), [signal](<https://devfeed.tech/tags/signal.md>)

### AI overview

The article's central takeaway is to manage agents around clear outcomes, then expand their autonomy as their work proves reliable while keeping humans accountable. It describes defining verifiable goals, such as tests that specify component inputs and outputs, and using feedback and observability to check results. For larger fleets, it recommends monitoring success rate, cost, and latency by agent, version, or model, then tracing individual conversations to investigate anomalies. The excerpt notes failure modes that may not raise error alerts, including runaway loops, deteriorating performance as context grows, and rule-breaking production queries. It presents tracing, including OpenTelemetry support, as a way to inspect agent activity, while acknowledging that fleet-level oversight depends on having agent conversations traced.

### Source excerpt

Recapping the questions that came up at Innovation Week: what a good goal looks like, how an agent earns more autonomy, how to get a fleet-wide signal, and what stays human as agents take on more of the work.

## Honeycomb Team Agents: AI SRE Done Right

DevFeed: [Honeycomb Team Agents: AI SRE Done Right](<https://devfeed.tech/articles/honeycomb-team-agents-ai-sre-done-right-116347.md>)

Original publisher: [Read original article](<https://www.honeycomb.io/blog/honeycomb-team-agents-ai-sre-done-right>)

Author: Dan Juengst

Published: 2026-11-03T13:58:00Z

Content type: opinion

Language: en

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

Topics: [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [LLM observability](<https://devfeed.tech/topics/llm-observability.md>), [human in the loop agent](<https://devfeed.tech/topics/human-in-the-loop-agent.md>)

Tags: [actions](<https://devfeed.tech/tags/actions.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-llms](<https://devfeed.tech/tags/ai-llms.md>), [ai-sre](<https://devfeed.tech/tags/ai-sre.md>), [alert](<https://devfeed.tech/tags/alert.md>), [alerts](<https://devfeed.tech/tags/alerts.md>), [audit](<https://devfeed.tech/tags/audit.md>), [autonomy](<https://devfeed.tech/tags/autonomy.md>), [cost](<https://devfeed.tech/tags/cost.md>), [goals](<https://devfeed.tech/tags/goals.md>), [incidents](<https://devfeed.tech/tags/incidents.md>), [instrumentation](<https://devfeed.tech/tags/instrumentation.md>), [personal](<https://devfeed.tech/tags/personal.md>), [product-updates](<https://devfeed.tech/tags/product-updates.md>), [production](<https://devfeed.tech/tags/production.md>), [quality](<https://devfeed.tech/tags/quality.md>), [releases](<https://devfeed.tech/tags/releases.md>), [risk](<https://devfeed.tech/tags/risk.md>), [sre](<https://devfeed.tech/tags/sre.md>), [team](<https://devfeed.tech/tags/team.md>)

### AI overview

Honeycomb Team Agents are designed to prevent reliability problems through background checks tied to team-defined goals, alongside personal agents that answer production questions with evidence. Team agents can check post-deploy latency and errors, monitor spend, review instrumentation, investigate alerts, compare AI evaluations with live traces, and draft knowledge updates. They use high-cardinality traces and optional MCP-connected data; findings link to supporting queries, traces, or deploys, and label numbers as measured, derived, estimated, or unset. Team memory records past failures and fixes with sources and team corrections. Autonomy is configurable by goal and tool, from observation and recommendations through human-approved actions to bounded autonomous operation; the article says greater autonomy suits lower-risk services with strong SLO coverage, while novel, high-impact failures remain human-led. The excerpt says personal agents are included on every Honeycomb plan and team agents are for Pro and Enterprise through Honeycomb Intelligence, priced by agent-work hours.

### Source excerpt

Honeycomb Team Agents are AI SRE coworkers that join your team proactively, not just reactively. Personal agents answer questions about production with evidence; team agents run on goals you define, checking releases, instrumentation, cost, agent quality, and resolving incidents with autonomy you match to risk.

## Our Limits Are Not Our Imagination

DevFeed: [Our Limits Are Not Our Imagination](<https://devfeed.tech/articles/our-limits-are-not-our-imagination-91113.md>)

Original publisher: [Read original article](<https://www.honeycomb.io/blog/our-limits-are-not-our-imagination>)

Author: Jessica Kerr (Jessitron)

Published: 2026-10-20T13:14:00Z

Content type: opinion

Language: en

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

Topics: [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [Formal verification](<https://devfeed.tech/topics/formal-verification.md>), [Test automation](<https://devfeed.tech/topics/test-automation.md>), [Code review](<https://devfeed.tech/topics/code-review.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [agile](<https://devfeed.tech/tags/agile.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-llms](<https://devfeed.tech/tags/ai-llms.md>), [ai-native](<https://devfeed.tech/tags/ai-native.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [automated](<https://devfeed.tech/tags/automated.md>), [aws](<https://devfeed.tech/tags/aws.md>), [bugs](<https://devfeed.tech/tags/bugs.md>), [capabilities](<https://devfeed.tech/tags/capabilities.md>), [code](<https://devfeed.tech/tags/code.md>), [deprecated](<https://devfeed.tech/tags/deprecated.md>), [development](<https://devfeed.tech/tags/development.md>), [formal-verification](<https://devfeed.tech/tags/formal-verification.md>), [imagination](<https://devfeed.tech/tags/imagination.md>), [property-based-testing](<https://devfeed.tech/tags/property-based-testing.md>), [review](<https://devfeed.tech/tags/review.md>), [software-engineering](<https://devfeed.tech/tags/software-engineering.md>), [system](<https://devfeed.tech/tags/system.md>), [testing](<https://devfeed.tech/tags/testing.md>), [verification](<https://devfeed.tech/tags/verification.md>)

### AI overview

The article argues that AI can make software development more rigorous when the surrounding system is designed for quality, rather than used only to produce familiar work faster. It gives examples including property-based tests, formal verification, architecture checks, observability, and multiple agent reviews; one developer cited works on greenfield software, where these practices can be established from the start. It recommends stepping back when AI produces poor code and improving the process with deterministic tests, instrumentation, removal of deprecated patterns, and evaluation of reviewers. The article also notes that agent capability alone does not ensure good software: guidance and the whole development system matter, including verification and impact reporting after production.

### Source excerpt

AI doesn't just make coding faster--used well, it can make code more rigorous than anything we wrote unassisted: property-based testing, formal verification, strict architecture checks, and more review than ever. The ceiling isn't our imagination. It's the development system we build around the agent.

## Everything We Talked About at O11yDay London 2026

DevFeed: [Everything We Talked About at O11yDay London 2026](<https://devfeed.tech/articles/everything-we-talked-about-at-o11yday-london-2026-88750.md>)

Original publisher: [Read original article](<https://www.honeycomb.io/blog/everything-we-talked-about-o11yday-london-2026>)

Author: Ken Rimple

Published: 2026-10-16T14:26:42Z

Content type: article

Language: en

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

Topics: [observability](<https://devfeed.tech/topics/observability.md>), [agent observability](<https://devfeed.tech/topics/agent-observability.md>), [OpenTelemetry](<https://devfeed.tech/topics/opentelemetry.md>), [Production Engineering](<https://devfeed.tech/topics/production-engineering.md>)

Tags: [agents-in-production](<https://devfeed.tech/tags/agents-in-production.md>), [ai-cost](<https://devfeed.tech/tags/ai-cost.md>), [ai-systems](<https://devfeed.tech/tags/ai-systems.md>), [conferences-meetups](<https://devfeed.tech/tags/conferences-meetups.md>), [observability](<https://devfeed.tech/tags/observability.md>), [software-engineering](<https://devfeed.tech/tags/software-engineering.md>)

### AI overview

The O11yDay London recap reports on teams using AI agents in software development and operations. Sessions covered code review and engineering workflows, agent evaluation, incident response, observability, and AI costs. Across the talks, speakers emphasized instrumentation and measurement to understand agent behavior and its effects in production.

### Source excerpt

A recap of every session at O11yDay London 2026, from Sam Newman's cobots and dark factories to Corey Quinn on AI cost observability, plus how Honeycomb debugs its own agents with Canvas, Agent Timeline, and AI Ecosystem.

## Honeycomb Adds Another AWS Competency: Resilience Technology

DevFeed: [Honeycomb Adds Another AWS Competency: Resilience Technology](<https://devfeed.tech/articles/honeycomb-adds-another-aws-competency-resilience-technology-87073.md>)

Original publisher: [Read original article](<https://www.honeycomb.io/blog/honeycomb-aws-resilience-technology-competency>)

Author: Jack Grisanti

Published: 2026-10-14T13:00:00Z

Content type: news

Language: en

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

Topics: [Resilience](<https://devfeed.tech/topics/resilience.md>), [observability](<https://devfeed.tech/topics/observability.md>), [Amazon Web Services](<https://devfeed.tech/topics/aws.md>)

Tags: [news-announcements](<https://devfeed.tech/tags/news-announcements.md>), [product-updates](<https://devfeed.tech/tags/product-updates.md>)

### AI overview

Honeycomb has earned the AWS Resilience Technology Competency for helping customers detect, investigate, and recover from production failures. The announcement describes real-time telemetry, anomaly detection, root cause analysis, incident response integrations, and support for AWS services.

### Source excerpt

Honeycomb has achieved the Resilience Technology AWS Competency, recognizing its ability to help customers detect, investigate, and recover from failures in production systems running on AWS.

## Honeycomb Is Hiring a New VP of Engineering

DevFeed: [Honeycomb Is Hiring a New VP of Engineering](<https://devfeed.tech/articles/honeycomb-is-hiring-a-new-vp-of-engineering-86192.md>)

Original publisher: [Read original article](<https://www.honeycomb.io/blog/honeycomb-hiring-vp-engineering>)

Author: Charity Majors

Published: 2026-10-13T20:46:52Z

Content type: news

Language: en

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

Topics: [engineering-leadership](<https://devfeed.tech/topics/engineering-leadership.md>), [Loop Engineering](<https://devfeed.tech/topics/loop-engineering.md>), [AI-enhanced product development](<https://devfeed.tech/topics/ai-enhanced-product-development.md>), [future of software](<https://devfeed.tech/topics/future-of-software.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [ai](<https://devfeed.tech/tags/ai.md>), [burnout](<https://devfeed.tech/tags/burnout.md>), [culture](<https://devfeed.tech/tags/culture.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [hiring](<https://devfeed.tech/tags/hiring.md>), [leading](<https://devfeed.tech/tags/leading.md>), [news-announcements](<https://devfeed.tech/tags/news-announcements.md>), [product](<https://devfeed.tech/tags/product.md>), [vp-of-engineering](<https://devfeed.tech/tags/vp-of-engineering.md>)

### AI overview

Honeycomb is recruiting a VP of Engineering to join its executive team and lead engineering strategy, organization, and execution. The role calls for partnership with product, experience leading through change, and recent hands-on software development using AI tools.

### Source excerpt

Honeycomb is hiring a new VP of Engineering as Emily Nakashima moves into an operational role after nine years leading engineering. We're looking for a partner to SVP Product Graham Siener.

## OpenTelemetry Collector Configuration for LLM Observability

DevFeed: [OpenTelemetry Collector Configuration for LLM Observability](<https://devfeed.tech/articles/opentelemetry-collector-configuration-for-llm-observability-77923.md>)

Original publisher: [Read original article](<https://www.honeycomb.io/blog/otel-collector-llm-observability>)

Author: Mike Goldsmith

Published: 2026-10-07T13:00:00Z

Content type: tutorial

Language: en

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

Topics: [LLM observability](<https://devfeed.tech/topics/llm-observability.md>), [OpenTelemetry](<https://devfeed.tech/topics/opentelemetry.md>), [ai observability](<https://devfeed.tech/topics/ai-observability.md>), [observability](<https://devfeed.tech/topics/observability.md>), [tracing](<https://devfeed.tech/topics/tracing.md>), [Grafana Cloud](<https://devfeed.tech/topics/grafana-cloud.md>)

Tags: [api-keys](<https://devfeed.tech/tags/api-keys.md>), [authentication](<https://devfeed.tech/tags/authentication.md>), [best-practices](<https://devfeed.tech/tags/best-practices.md>), [collector](<https://devfeed.tech/tags/collector.md>), [instrumentation](<https://devfeed.tech/tags/instrumentation.md>), [llm-observability](<https://devfeed.tech/tags/llm-observability.md>), [observability](<https://devfeed.tech/tags/observability.md>), [opentelemetry](<https://devfeed.tech/tags/opentelemetry.md>), [schemas](<https://devfeed.tech/tags/schemas.md>), [semantic](<https://devfeed.tech/tags/semantic.md>), [technical-deep-dives](<https://devfeed.tech/tags/technical-deep-dives.md>), [traces](<https://devfeed.tech/tags/traces.md>), [troubleshooting](<https://devfeed.tech/tags/troubleshooting.md>), [validation](<https://devfeed.tech/tags/validation.md>)

### AI overview

This tutorial walks through configuring the OpenTelemetry Collector to receive LLM traces over OTLP, normalize different GenAI telemetry schemas, redact sensitive content, manage data volume, and export traces to Honeycomb. It also covers validating the pipeline and troubleshooting common configuration problems.

### Source excerpt

A complete, annotated OpenTelemetry Collector configuration for LLM observability: receiving traces over OTLP, normalizing OpenInference/OpenLLMetry schemas onto GenAI semantic conventions, redacting sensitive prompt and completion content, managing volume without sampling away conversations, exporting to Honeycomb, plus validation steps and a troubleshooting table.

## How Honeycomb Private Cloud Automates Drift Reporting and Triage

DevFeed: [How Honeycomb Private Cloud Automates Drift Reporting and Triage](<https://devfeed.tech/articles/how-honeycomb-private-cloud-drinks-from-the-fire-hose-77911.md>)

Original publisher: [Read original article](<https://www.honeycomb.io/blog/how-honeycomb-private-cloud-drinks-from-the-fire-hose>)

Author: Fred Hebert

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

Content type: article

Language: en

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

Topics: [LLM security](<https://devfeed.tech/topics/llm-security.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>), [observability](<https://devfeed.tech/topics/observability.md>)

Tags: [ai-llms](<https://devfeed.tech/tags/ai-llms.md>), [ai-workflows](<https://devfeed.tech/tags/ai-workflows.md>), [automation](<https://devfeed.tech/tags/automation.md>), [ci](<https://devfeed.tech/tags/ci.md>), [software-engineering](<https://devfeed.tech/tags/software-engineering.md>)

### AI overview

The Honeycomb Private Cloud team created a drift report to track changes across teams' repositories, then refactored its configuration to make comparisons easier. The workflow grew to include daily reports, an AI-assisted triage skill, and ticket suggestions. The article emphasizes deterministic steps, gradual automation, and coordination as ways to make the process easier to inspect and adapt.

### Source excerpt

This post walks through how the Honeycomb Private Cloud team built an automated drift report, refactored their own config to make diffing possible, and layered on an AI triage skill to keep pace with changes across the org--plus the guiding principles that made the automation trustworthy.

## Dr. Cat Hicks on the Psychology of Software Teams

DevFeed: [Dr. Cat Hicks on the Psychology of Software Teams](<https://devfeed.tech/articles/dr-cat-hicks-on-the-psychology-of-software-teams-77897.md>)

Original publisher: [Read original article](<https://www.honeycomb.io/blog/cat-hicks-psychology-of-software-teams>)

Author: Rox Williams

Published: 2026-10-01T13:00:00Z

Content type: article

Language: en

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

Topics: [engineering-leadership](<https://devfeed.tech/topics/engineering-leadership.md>), [trust](<https://devfeed.tech/topics/trust.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [engineering-culture](<https://devfeed.tech/topics/engineering-culture.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-identity](<https://devfeed.tech/tags/ai-identity.md>), [ai-llms](<https://devfeed.tech/tags/ai-llms.md>), [observability](<https://devfeed.tech/tags/observability.md>), [software-engineering](<https://devfeed.tech/tags/software-engineering.md>), [teams](<https://devfeed.tech/tags/teams.md>), [trust](<https://devfeed.tech/tags/trust.md>)

### AI overview

Dr. Cat Hicks discusses how AI can affect trust, identity, and anxiety within software teams. She argues that leaders can reduce identity threat by setting clear expectations and standards, measuring perceptions of organizational fairness, and creating accountability for harmful behavior. She also cautions against tying professional identity too closely to expertise in one programming language or historical context.

### Source excerpt

Dr. Cat Hicks, author of The Psychology of Software Teams and founder of Catharsis, joins Charity Majors for episode two of Leading With Observability. They talk organizational trust in AI, identity threat among developers, and how leaders can create the structure that reduces anxiety in this new era.

## How Honeycomb refreshed its UI with a new heatmap color ramp

DevFeed: [How Honeycomb refreshed its UI with a new heatmap color ramp](<https://devfeed.tech/articles/a-peek-behind-our-ui-refresh-77928.md>)

Original publisher: [Read original article](<https://www.honeycomb.io/blog/soft-launch-sharper-signals-ui-refresh>)

Author: Sol Escalada

Published: 2026-09-30T13:00:00Z

Content type: article

Language: en

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

Topics: [User interface design](<https://devfeed.tech/topics/ui-design.md>), [Data visualization](<https://devfeed.tech/topics/data-visualization.md>), [Dark Mode](<https://devfeed.tech/topics/dark-mode.md>)

Tags: [accessibility](<https://devfeed.tech/tags/accessibility.md>), [design-system](<https://devfeed.tech/tags/design-system.md>), [software-engineering](<https://devfeed.tech/tags/software-engineering.md>), [teams-collaboration](<https://devfeed.tech/tags/teams-collaboration.md>), [ui](<https://devfeed.tech/tags/ui.md>)

### AI overview

Honeycomb describes a UI refresh that addressed accumulated design drift through updates to its design system, including refined shadows, rounder controls, and consistent motion guidance. The team also introduced a magma-inspired heatmap color ramp that improves distinction between values and works in light and dark modes, with colorblind filters considered during selection.

### Source excerpt

Sol walks through the reasoning behind a recent UI refresh: softer shadows and rounder corners, a new magma-inspired heatmap color ramp tuned for dark mode and accessibility, and small polish that makes a dense product feel calmer.

## Agents Need Context: Introducing Canvas Connectors, Fleet-wide AI Agent Visibility, and More

DevFeed: [Agents Need Context: Introducing Canvas Connectors, Fleet-wide AI Agent Visibility, and More](<https://devfeed.tech/articles/agents-need-context-introducing-canvas-connectors-fleet-wide-ai-agent-visibility-and-more-77888.md>)

Original publisher: [Read original article](<https://www.honeycomb.io/blog/agents-need-context-canvas-connectors-ai-agent-visibility>)

Author: Dan Juengst

Published: 2026-09-29T12:57:00Z

Content type: release

Language: en

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

Topics: [LLM observability](<https://devfeed.tech/topics/llm-observability.md>), [agent orchestration](<https://devfeed.tech/topics/agent-orchestration.md>), [OpenTelemetry](<https://devfeed.tech/topics/opentelemetry.md>), [MSP MCP](<https://devfeed.tech/topics/msp-mcp.md>)

Tags: [agent-fleets](<https://devfeed.tech/tags/agent-fleets.md>), [agents-in-production](<https://devfeed.tech/tags/agents-in-production.md>), [ai-agent-visibility](<https://devfeed.tech/tags/ai-agent-visibility.md>), [ai-llms](<https://devfeed.tech/tags/ai-llms.md>), [better](<https://devfeed.tech/tags/better.md>), [product-updates](<https://devfeed.tech/tags/product-updates.md>)

### AI overview

Honeycomb announces Canvas Connectors that bring code repositories, incidents, runbooks, tickets and product analytics into AI-assisted production investigations. The release also adds fleet-wide agent performance and cost views in early access, makes anomaly detection generally available, and introduces guided onboarding through coding agents. It describes donating adaptive tail sampling algorithms to the OpenTelemetry Collector.

### Source excerpt

Canvas agents can now read your code, incidents, runbooks and tickets, to get to the right solution, first time. Also new: AI Ecosystem and LLM cost tracking in early access, Anomaly Detection GA, and onboarding from your coding agent.

## Introducing AI Ecosystem: Zoom Out to See Your Whole AI Agent Fleet

DevFeed: [Introducing AI Ecosystem: Zoom Out to See Your Whole AI Agent Fleet](<https://devfeed.tech/articles/introducing-ai-ecosystem-zoom-out-to-see-your-whole-ai-agent-fleet-77917.md>)

Original publisher: [Read original article](<https://www.honeycomb.io/blog/introducing-ai-ecosystem>)

Author: Dan Juengst

Published: 2026-09-29T12:57:00Z

Content type: release

Language: en

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

Topics: [LLM observability](<https://devfeed.tech/topics/llm-observability.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>)

Tags: [ai-agent-observability](<https://devfeed.tech/tags/ai-agent-observability.md>), [ai-llms](<https://devfeed.tech/tags/ai-llms.md>), [product-updates](<https://devfeed.tech/tags/product-updates.md>)

### AI overview

Honeycomb announced early access to AI Ecosystem, an analysis layer for production AI agent fleets. It combines fleet health metrics, estimated LLM costs, and drilldowns into individual conversations through Agent Timeline. Cost estimates use a public price table, and teams already supplying Agent Timeline spans can reuse that telemetry.

### Source excerpt

Honeycomb is announcing early access to AI Ecosystem: an AI agent fleet-level analysis layer built on Honeycomb's context-rich data model. It covers AI Agent Fleet Performance, LLM Cost Tracking, and Agent Conversations, with one-click drilldown from any fleet-level signal into the exact conversation on Agent Timeline that explains it.

## How Adaptive Tail Sampling Works in the OpenTelemetry Collector

DevFeed: [How Adaptive Tail Sampling Works in the OpenTelemetry Collector](<https://devfeed.tech/articles/how-adaptive-tail-sampling-works-in-the-opentelemetry-collector-77909.md>)

Original publisher: [Read original article](<https://www.honeycomb.io/blog/how-adaptive-tail-sampling-works>)

Author: Mike Goldsmith

Published: 2026-09-21T13:00:00Z

Content type: tutorial

Language: en

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

Topics: [OpenTelemetry](<https://devfeed.tech/topics/opentelemetry.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>)

Tags: [collector](<https://devfeed.tech/tags/collector.md>), [opentelemetry](<https://devfeed.tech/tags/opentelemetry.md>), [performance](<https://devfeed.tech/tags/performance.md>), [pipeline](<https://devfeed.tech/tags/pipeline.md>), [sampling](<https://devfeed.tech/tags/sampling.md>), [technical-deep-dives](<https://devfeed.tech/tags/technical-deep-dives.md>)

### AI overview

The article explains Honeycomb's adaptive tail-sampling processor for the OpenTelemetry Collector, including how traces are buffered and sampled, how thresholds preserve statistical weighting across pipeline stages, sampler options, performance results, deployment constraints, and differences from Refinery.

### Source excerpt

A technical deep dive into Honeycomb's adaptive tail sampling processor for the OpenTelemetry Collector: how decisions get made, the samplers available, how thresholds compose with the rest of a sampling pipeline, performance benchmarks, deployment limitations, and how it compares to Refinery.

## How Canvas Powers the AI Agent Development Feedback Loop

DevFeed: [How Canvas Powers the AI Agent Development Feedback Loop](<https://devfeed.tech/articles/how-canvas-powers-the-ai-agent-development-feedback-loop-77910.md>)

Original publisher: [Read original article](<https://www.honeycomb.io/blog/how-canvas-powers-ai-agent-development-feedback-loop>)

Author: Jodi Sloan

Published: 2026-09-14T13:00:00Z

Content type: tutorial

Language: en

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

Topics: [ai observability](<https://devfeed.tech/topics/ai-observability.md>), [OpenTelemetry](<https://devfeed.tech/topics/opentelemetry.md>), [Claude Code](<https://devfeed.tech/topics/claude-code.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-llms](<https://devfeed.tech/tags/ai-llms.md>), [development](<https://devfeed.tech/tags/development.md>), [opentelemetry](<https://devfeed.tech/tags/opentelemetry.md>), [tracing](<https://devfeed.tech/tags/tracing.md>)

### AI overview

This tutorial presents Honeycomb Canvas as a workspace for improving AI agents through a feedback loop: instrumenting runs with OpenTelemetry, investigating individual and recurring failures, prioritizing and shipping fixes, and comparing production metrics before and after changes. It also describes evaluation, cost and latency analysis, monitoring, and collaboration features. GitHub and Linear connectors are in beta, with general availability expected in fall 2026.

### Source excerpt

AI agents need a real feedback loop, not just reactive debugging. This post walks through how Honeycomb's Canvas powers each stage--instrumenting agents with OpenTelemetry, understanding a single run, finding the problems worth fixing, shipping the fix, and proving it worked--plus tips for getting the most out of Canvas.

## AI Norms & Values, Part 3 of 3: Things We Hold True

DevFeed: [AI Norms & Values, Part 3 of 3: Things We Hold True](<https://devfeed.tech/articles/ai-norms-values-part-3-of-3-things-we-hold-true-77893.md>)

Original publisher: [Read original article](<https://www.honeycomb.io/blog/ai-norms-values-part-3-things-we-hold-true>)

Author: Charity Majors

Published: 2026-09-09T13:00:00Z

Content type: article

Language: en

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

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [engineering-culture](<https://devfeed.tech/topics/engineering-culture.md>), [ai-governance](<https://devfeed.tech/topics/ai-governance.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-at-work](<https://devfeed.tech/tags/ai-at-work.md>), [ai-llms](<https://devfeed.tech/tags/ai-llms.md>), [breach](<https://devfeed.tech/tags/breach.md>), [coaching](<https://devfeed.tech/tags/coaching.md>), [code](<https://devfeed.tech/tags/code.md>), [culture](<https://devfeed.tech/tags/culture.md>)

### AI overview

Honeycomb's final AI norms and values installment describes AI as a tool that should amplify human skill while leaving people accountable for their work. It sets expectations for AI use in communication, software artifacts, and management, emphasizing clarity, consent, review, and trust. The article also outlines the company's positions on AI-related energy use, intellectual property, bias, privacy, and employment.

### Source excerpt

The final part of Honeycomb's AI Norms & Values series: the principles the company holds true about AI as a tool, ownership of work, and rising standards; how it actually uses AI day to day; usage patterns for respecting each other's time; and where it stands on AI's ethical externalities like energy use, IP, bias, and wages.

## Wide Events vs. Three Pillars: AI Observability Costs

DevFeed: [Wide Events vs. Three Pillars: AI Observability Costs](<https://devfeed.tech/articles/wide-events-vs-three-pillars-ai-observability-costs-77934.md>)

Original publisher: [Read original article](<https://www.honeycomb.io/blog/wide-events-vs-three-pillars-ai-observability-costs>)

Author: Nick Travaglini

Published: 2026-09-08T13:00:00Z

Content type: article

Language: en

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

Topics: [LLM observability](<https://devfeed.tech/topics/llm-observability.md>), [ai observability](<https://devfeed.tech/topics/ai-observability.md>), [cost-optimization](<https://devfeed.tech/topics/cost-optimization.md>), [Event-Streaming](<https://devfeed.tech/topics/event-streaming.md>), [OpenTelemetry](<https://devfeed.tech/topics/opentelemetry.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-llms](<https://devfeed.tech/tags/ai-llms.md>), [ai-observability](<https://devfeed.tech/tags/ai-observability.md>), [costs](<https://devfeed.tech/tags/costs.md>), [engineering-best-practices](<https://devfeed.tech/tags/engineering-best-practices.md>), [observability](<https://devfeed.tech/tags/observability.md>), [telemetry](<https://devfeed.tech/tags/telemetry.md>)

### AI overview

This article compares the traditional three pillars of observability with wide events for monitoring AI applications and agents. It argues that wide events can reduce duplicated telemetry storage and query costs while retaining the context engineers need to investigate behavior, and recommends reviewing which data must remain at request level versus what can be aggregated.

### Source excerpt

AI agents make telemetry costs harder to predict. This post compares the three pillars against the wide event model, and explains why wide events keep AI observability costs predictable without sacrificing the context engineers need.

## How Honeycomb Relational Queries Combine Data Across a Trace

DevFeed: [How Honeycomb Relational Queries Combine Data Across a Trace](<https://devfeed.tech/articles/relational-query-superpowers-77925.md>)

Original publisher: [Read original article](<https://www.honeycomb.io/blog/relational-query-superpowers>)

Author: Ken Rimple

Published: 2026-09-07T13:00:00Z

Content type: tutorial

Language: en

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

Topics: [Query (disambiguation)](<https://devfeed.tech/topics/query.md>), [Grafana](<https://devfeed.tech/topics/grafana.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [gateway](<https://devfeed.tech/tags/gateway.md>), [investigation](<https://devfeed.tech/tags/investigation.md>), [observability](<https://devfeed.tech/tags/observability.md>), [query](<https://devfeed.tech/tags/query.md>), [trace](<https://devfeed.tech/tags/trace.md>), [tracing](<https://devfeed.tech/tags/tracing.md>), [tutorials](<https://devfeed.tech/tags/tutorials.md>)

### AI overview

A walkthrough of Honeycomb relational query operators shows how to combine attributes from multiple spans in one trace. Using a checkout error investigation, it demonstrates querying child exception details, root span information, and attributes from other spans with the any, any2, and any3 prefixes. It also covers excluding traces with none and using the results in boards and other views.

### Source excerpt

See how Honeycomb's relational query keywords--root, parent, child, any, any2, any3, and none--let you pull attributes from anywhere in a single trace into one query, walked through with a real checkout-error investigation.

## AI Norms & Values, Part 2 of 3: AI for Honeycomb Engineering

DevFeed: [AI Norms & Values, Part 2 of 3: AI for Honeycomb Engineering](<https://devfeed.tech/articles/ai-norms-values-part-2-of-3-ai-for-honeycomb-engineering-77892.md>)

Original publisher: [Read original article](<https://www.honeycomb.io/blog/ai-norms-values-part-2-ai-honeycomb-engineering>)

Author: Charity Majors

Published: 2026-09-02T13:00:00Z

Content type: article

Language: en

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

Topics: [AI-enhanced product development](<https://devfeed.tech/topics/ai-enhanced-product-development.md>), [engineering-leadership](<https://devfeed.tech/topics/engineering-leadership.md>), [Loop Engineering](<https://devfeed.tech/topics/loop-engineering.md>)

Tags: [agentic-workflows](<https://devfeed.tech/tags/agentic-workflows.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-assisted](<https://devfeed.tech/tags/ai-assisted.md>), [ai-llms](<https://devfeed.tech/tags/ai-llms.md>), [ai-platform](<https://devfeed.tech/tags/ai-platform.md>), [culture](<https://devfeed.tech/tags/culture.md>), [engineering](<https://devfeed.tech/tags/engineering.md>)

### AI overview

Honeycomb's engineering leadership describes its AI adoption goals, including applying AI throughout the software development lifecycle, experimenting with agentic workflows, and seeking productivity gains while maintaining reliability and sustainable incident response. The article also shares guidance on experimentation, team practices, and the changing nature of engineering work.

### Source excerpt

Charity Majors shares a note from Emily Nakashima, SVP of Engineering, on why Honeycomb's engineering org is going all in on AI, the north star it's aiming for, and an honest FAQ about what that means day to day.

## Bringing the Most Advanced Sampling to the OpenTelemetry Collector

DevFeed: [Bringing the Most Advanced Sampling to the OpenTelemetry Collector](<https://devfeed.tech/articles/bringing-the-most-advanced-sampling-to-the-opentelemetry-collector-77896.md>)

Original publisher: [Read original article](<https://www.honeycomb.io/blog/bringing-most-advanced-sampling-opentelemetry-collector>)

Author: Mike Goldsmith

Published: 2026-09-01T13:00:00Z

Content type: article

Language: en

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

Topics: [OpenTelemetry](<https://devfeed.tech/topics/opentelemetry.md>), [observability](<https://devfeed.tech/topics/observability.md>)

Tags: [adaptive](<https://devfeed.tech/tags/adaptive.md>), [cost-control](<https://devfeed.tech/tags/cost-control.md>), [observability](<https://devfeed.tech/tags/observability.md>), [opentelemetry](<https://devfeed.tech/tags/opentelemetry.md>), [sampling](<https://devfeed.tech/tags/sampling.md>), [trace](<https://devfeed.tech/tags/trace.md>), [work](<https://devfeed.tech/tags/work.md>)

### AI overview

Honeycomb is donating an adaptive tail sampling processor to the OpenTelemetry Collector. The article explains how trace fingerprinting distributes sampling across different request patterns, how percentage and throughput targets adjust sample rates, and how sample rate attribution can help backends interpret trace analytics. It also provides configuration examples for trying the processor with Honeycomb Collector Distribution, Kubernetes, or Docker.

### Source excerpt

Honeycomb is donating its adaptive tail sampling processor, built on years of Refinery experience, to the OpenTelemetry Collector. See how adaptive sampling, trace fingerprinting, and sample rate attribution work, and how to try it today with the Honeycomb Collector Distribution.

## Fin's CTO on Building Great Engineering Organizations in the AI Era

DevFeed: [Fin's CTO on Building Great Engineering Organizations in the AI Era](<https://devfeed.tech/articles/fin-s-cto-on-building-great-engineering-organizations-in-the-ai-era-77903.md>)

Original publisher: [Read original article](<https://www.honeycomb.io/blog/fin-cto-building-great-engineering-organizations-ai-era>)

Author: Rox Williams

Published: 2026-08-31T13:00:00Z

Content type: article

Language: en

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

Topics: [engineering-leadership](<https://devfeed.tech/topics/engineering-leadership.md>), [engineering-culture](<https://devfeed.tech/topics/engineering-culture.md>), [observability](<https://devfeed.tech/topics/observability.md>), [Code review](<https://devfeed.tech/topics/code-review.md>), [AI-enhanced product development](<https://devfeed.tech/topics/ai-enhanced-product-development.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-llms](<https://devfeed.tech/tags/ai-llms.md>), [charity-majors](<https://devfeed.tech/tags/charity-majors.md>), [cto](<https://devfeed.tech/tags/cto.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [engineering-productivity](<https://devfeed.tech/tags/engineering-productivity.md>), [leadership](<https://devfeed.tech/tags/leadership.md>), [observability](<https://devfeed.tech/tags/observability.md>), [software-engineering](<https://devfeed.tech/tags/software-engineering.md>)

### AI overview

Fin CTO Darragh Curran discusses how the company nearly tripled its goal for engineering productivity through AI-assisted coding, automated pull request review, observability, and hands-on leadership. He describes rapid experimentation and measurement as ways to improve software teams and maintain trust in automated reviews.

### Source excerpt

Fin (formerly Intercom) CTO Darragh Curran set a public goal to double engineering productivity--and nearly tripled it. In the first episode of Leading With Observability, he talks with Charity Majors about AI-driven PR review, hands-on leadership through the transition, and why observability is the trust mechanism that makes it all work.

## 7 Best Datadog Alternatives for AI and Agent Observability

DevFeed: [7 Best Datadog Alternatives for AI and Agent Observability](<https://devfeed.tech/articles/7-best-datadog-alternatives-for-ai-and-agent-observability-77899.md>)

Original publisher: [Read original article](<https://www.honeycomb.io/blog/datadog-alternatives>)

Author: Kale Bogdanovs

Published: 2026-08-26T20:01:00Z

Content type: comparison

Language: en

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

Topics: [LLM observability](<https://devfeed.tech/topics/llm-observability.md>), [observability](<https://devfeed.tech/topics/observability.md>), [OpenTelemetry](<https://devfeed.tech/topics/opentelemetry.md>), [tracing](<https://devfeed.tech/topics/tracing.md>), [Grafana](<https://devfeed.tech/topics/grafana.md>), [experiments](<https://devfeed.tech/topics/experiments.md>)

Tags: [ai-and-machine-learning](<https://devfeed.tech/tags/ai-and-machine-learning.md>), [ai-llms](<https://devfeed.tech/tags/ai-llms.md>), [ai-monitoring](<https://devfeed.tech/tags/ai-monitoring.md>), [datadog](<https://devfeed.tech/tags/datadog.md>), [dynatrace](<https://devfeed.tech/tags/dynatrace.md>), [grafana](<https://devfeed.tech/tags/grafana.md>), [new-relic](<https://devfeed.tech/tags/new-relic.md>), [observability](<https://devfeed.tech/tags/observability.md>), [opentelemetry](<https://devfeed.tech/tags/opentelemetry.md>), [phoenix](<https://devfeed.tech/tags/phoenix.md>), [signoz](<https://devfeed.tech/tags/signoz.md>)

### AI overview

This guide compares seven Datadog alternatives for teams evaluating observability across application and AI workloads. It weighs production investigation, AI and agent monitoring, telemetry costs, OpenTelemetry portability, deployment, and platform scope. Honeycomb is presented as a strong option for teams prioritizing exploratory production investigation and OpenTelemetry, while other platforms are matched to broader observability or more focused AI engineering needs.

### Source excerpt

Comparing Datadog alternatives for AI and agent observability? See how Honeycomb, New Relic, Dynatrace, Grafana Cloud, Phoenix, Langfuse, and SigNoz stack up on cost, investigation, and OpenTelemetry support.

## AI Norms & Values, Part 1 of 3: How We Do Business at Honeycomb

DevFeed: [AI Norms & Values, Part 1 of 3: How We Do Business at Honeycomb](<https://devfeed.tech/articles/ai-norms-values-part-1-of-3-how-we-do-business-at-honeycomb-77891.md>)

Original publisher: [Read original article](<https://www.honeycomb.io/blog/ai-norms-values-part-1-how-we-do-business-at-honeycomb>)

Author: Charity Majors

Published: 2026-08-20T14:50:39Z

Content type: opinion

Language: en

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

Topics: [Business, Industry, Usability, User Experience, User Research, Web Strategy](<https://devfeed.tech/topics/business-industry-usability-user-experience-user-research-web-strategy.md>), [AI interaction best practices](<https://devfeed.tech/topics/ai-interaction-best-practices.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-llms](<https://devfeed.tech/tags/ai-llms.md>), [business](<https://devfeed.tech/tags/business.md>), [culture](<https://devfeed.tech/tags/culture.md>)

### AI overview

Honeycomb reflects on a year of AI adoption and presents principles for how its go-to-market teams should use AI while working with customers. The principles emphasize creating customer value, communicating honestly, respecting attention, checking AI-assisted work, and building durable relationships.

### Source excerpt

It's been a year since Honeycomb issued its AI mandate. Charity reflects on what that produced, why AI isn't special (it just amplifies what's already there), and shares the first of three new documents on Honeycomb's AI norms and values: how we do business.

[Next page](<https://devfeed.tech/sources/honeycomb-blog.md?cursor=WyIyMDI2LTA4LTIwVDE0OjUwOjM5KzAwOjAwIiwgIjYwZjRhZmE1LWQyODktNDkwNi1iMWFmLTY1MjA0YTY0ZDcyMCJd>)