# Amplitude

Amplitude Blog RSS Feed

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

## How I built my next career chapter at Amplitude

DevFeed: [How I built my next career chapter at Amplitude](<https://devfeed.tech/articles/how-i-built-my-next-career-chapter-at-amplitude-134086.md>)

Original publisher: [Read original article](<https://amplitude.com/blog/employee-spotlight-martins>)

Author: Jose Martins

Published: 2026-11-13T00:00:00Z

Content type: opinion

Language: en

Sources: [Amplitude](<https://devfeed.tech/sources/amplitude.md>)

Topics: [Bootcamp](<https://devfeed.tech/topics/bootcamp.md>), [Learning](<https://devfeed.tech/topics/learning.md>), [Tech Careers](<https://devfeed.tech/topics/tech-careers.md>)

Tags: [2025](<https://devfeed.tech/tags/2025.md>), [about](<https://devfeed.tech/tags/about.md>), [ai](<https://devfeed.tech/tags/ai.md>), [all](<https://devfeed.tech/tags/all.md>), [also](<https://devfeed.tech/tags/also.md>), [amplitude](<https://devfeed.tech/tags/amplitude.md>), [award](<https://devfeed.tech/tags/award.md>), [build](<https://devfeed.tech/tags/build.md>), [building](<https://devfeed.tech/tags/building.md>), [business](<https://devfeed.tech/tags/business.md>), [but](<https://devfeed.tech/tags/but.md>), [career](<https://devfeed.tech/tags/career.md>), [customer](<https://devfeed.tech/tags/customer.md>), [customer-experience](<https://devfeed.tech/tags/customer-experience.md>), [digital](<https://devfeed.tech/tags/digital.md>), [experience](<https://devfeed.tech/tags/experience.md>), [i](<https://devfeed.tech/tags/i.md>), [inside-amplitude](<https://devfeed.tech/tags/inside-amplitude.md>), [manager](<https://devfeed.tech/tags/manager.md>), [my](<https://devfeed.tech/tags/my.md>), [program](<https://devfeed.tech/tags/program.md>)

### AI overview

As an Amplitude leadership-program project, Growth Lab helped customers learn product skills through one short video a day, peer collaboration, and leaderboard prizes. Jose Martins says the initiative grew from an EMEA project into a global program serving more than 600 companies and 1,600 participants, and led to his move from Senior Customer Success Manager to a newly created Digital Customer Experience Program Manager role. The excerpt presents the project as an example of building a career opportunity by developing an idea with organizational support.

### Source excerpt

Jose Martins shares the story of how he forged his own path to becoming Amplitude's Digital Customer Experience Program Manager

## What will you build with infinite engineers?

DevFeed: [What will you build with infinite engineers?](<https://devfeed.tech/articles/what-will-you-build-with-infinite-engineers-130652.md>)

Original publisher: [Read original article](<https://amplitude.com/blog/wave-launch>)

Author: Darshil Gandhi

Published: 2026-11-12T00:00:00Z

Content type: release

Language: en

Sources: [Amplitude](<https://devfeed.tech/sources/amplitude.md>)

Topics: [Product Management](<https://devfeed.tech/topics/product-management.md>), [product analytics](<https://devfeed.tech/topics/product-analytics.md>), [product-experimentation](<https://devfeed.tech/topics/product-experimentation.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ambition](<https://devfeed.tech/tags/ambition.md>), [amplitude](<https://devfeed.tech/tags/amplitude.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [analyst](<https://devfeed.tech/tags/analyst.md>), [analytics](<https://devfeed.tech/tags/analytics.md>), [approach](<https://devfeed.tech/tags/approach.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [area](<https://devfeed.tech/tags/area.md>), [behavior](<https://devfeed.tech/tags/behavior.md>), [best-practices](<https://devfeed.tech/tags/best-practices.md>), [customer](<https://devfeed.tech/tags/customer.md>), [decision](<https://devfeed.tech/tags/decision.md>), [improvements](<https://devfeed.tech/tags/improvements.md>), [next](<https://devfeed.tech/tags/next.md>), [product](<https://devfeed.tech/tags/product.md>), [results](<https://devfeed.tech/tags/results.md>), [ship](<https://devfeed.tech/tags/ship.md>)

### AI overview

Amplitude Wave connects product investigation and impact measurement to AI accelerated building. Teams set a business goal; Wave analyzes behavioral data, session replays, and customer feedback to identify Opportunities, recommend changes and test hypotheses, then measure results. Teams retain control over priorities and what reaches customers, while using product judgment to adapt recommendations. In examples, PixAI adapted a suggestion to guide new users to its Missions feature and reported higher Missions opens, publishing, and Day 1 retention. Amplitude used replay analysis to identify generic prompts that users rarely selected, then tested personalized suggestions, reporting about 160% more suggestion sends. DigitalOcean uses ranked Opportunities with experiment plans and can create Jira tickets from Wave. Wave is a paid offering for Growth and Enterprise customers; getting started includes assessing analytics and replay data. The excerpt presents these as company-reported examples and results.

### Source excerpt

Turn customer behavior into your next product decision with Amplitude Wave. Investigate opportunities, ship improvements, and measure results.

## How I use Wave to find Amplitude's next product improvement

DevFeed: [How I use Wave to find Amplitude's next product improvement](<https://devfeed.tech/articles/how-i-use-wave-to-find-amplitude-s-next-product-improvement-126468.md>)

Original publisher: [Read original article](<https://amplitude.com/blog/wave-product-improvements>)

Author: Jacob Newman

Published: 2026-11-09T00:00:00Z

Content type: article

Language: en

Sources: [Amplitude](<https://devfeed.tech/sources/amplitude.md>)

Topics: [product-experimentation](<https://devfeed.tech/topics/product-experimentation.md>), [UI/UX Design](<https://devfeed.tech/topics/ui-ux-design.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [AI-driven information retrieval](<https://devfeed.tech/topics/ai-driven-information-retrieval.md>), [implementation](<https://devfeed.tech/topics/implementation.md>)

Tags: [about](<https://devfeed.tech/tags/about.md>), [activation](<https://devfeed.tech/tags/activation.md>), [added](<https://devfeed.tech/tags/added.md>), [administrator](<https://devfeed.tech/tags/administrator.md>), [after](<https://devfeed.tech/tags/after.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [all](<https://devfeed.tech/tags/all.md>), [also](<https://devfeed.tech/tags/also.md>), [amplitude](<https://devfeed.tech/tags/amplitude.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [can](<https://devfeed.tech/tags/can.md>), [i](<https://devfeed.tech/tags/i.md>), [more](<https://devfeed.tech/tags/more.md>), [next](<https://devfeed.tech/tags/next.md>), [perspectives](<https://devfeed.tech/tags/perspectives.md>), [product](<https://devfeed.tech/tags/product.md>), [tasks](<https://devfeed.tech/tags/tasks.md>), [team](<https://devfeed.tech/tags/team.md>), [users](<https://devfeed.tech/tags/users.md>)

### AI overview

Amplitude uses Wave to connect replay and analytics evidence to product opportunities, proposed changes, implementation, and follow-up measurement; teams review the proposals before shipping. In a 100-replay analysis, users typed questions in 80 sessions while only 12 selected generic suggestions. Personalized cards based on recent chart or dashboard activity recorded 2.43 suggestion sends per 100 exposed users versus 0.94 for generic cards in an initial test, which still needs validation. Other shipped changes added paths from useful answers to Custom Agents or saved Notebook content, surfaced agent outputs through MCP, improved AI Feedback setup guidance, and clarified administrator prerequisites for Intercom and Zendesk connections. Reported outcomes vary: setup connection completion was 69.4%, while an HTTP API onboarding recommendation showed a directional, statistically inconclusive activation result. Wave also informed agent workflow changes and a docs search fix using a three-character minimum and about 200 ms debounce. Some proposals remain unconfirmed, and attribution or metric definitions still need work to assess impact.

### Source excerpt

See how the Amplitude team uses Wave to improve our AI agents, from more relevant suggestions to repeatable tasks and answers users can keep.

## How Wave makes me a better growth PM

DevFeed: [How Wave makes me a better growth PM](<https://devfeed.tech/articles/how-wave-makes-me-a-better-growth-pm-126467.md>)

Original publisher: [Read original article](<https://amplitude.com/blog/wave-product-friction>)

Author: Cassie Peretore

Published: 2026-11-09T00:00:00Z

Content type: article

Language: en

Sources: [Amplitude](<https://devfeed.tech/sources/amplitude.md>)

Topics: [UI/UX Design](<https://devfeed.tech/topics/ui-ux-design.md>), [product-experimentation](<https://devfeed.tech/topics/product-experimentation.md>)

Tags: [amplitude](<https://devfeed.tech/tags/amplitude.md>), [customers](<https://devfeed.tech/tags/customers.md>), [dashboard](<https://devfeed.tech/tags/dashboard.md>), [funnel](<https://devfeed.tech/tags/funnel.md>), [growth](<https://devfeed.tech/tags/growth.md>), [investigation](<https://devfeed.tech/tags/investigation.md>), [investigations](<https://devfeed.tech/tags/investigations.md>), [perspectives](<https://devfeed.tech/tags/perspectives.md>)

### AI overview

Amplitude Wave connects related customer feedback in Slack over time, keeping customer details together and preparing a problem summary, supporting evidence, and suggested solution outline so product teams can assess and act on friction without reconstructing reports themselves. The excerpt gives two examples: starting session replays about two seconds before a relevant funnel moment was followed by a 15% rise in average daily replay launches from those investigations over 30 days, sustained beyond launch; and improving Slack dashboard subscription setup with in-window reconnection, private-channel guidance, and manual channel ID entry led users to create 14.5% more subscriptions. These are reported outcomes from the author's examples, not claims about every use of Wave.

### Source excerpt

See how Cassie uses Amplitude Wave to fix replay, onboarding, and dashboard friction, and measure what changes for our customers.

## How DigitalOcean Improves Developer Onboarding With Wave

DevFeed: [How DigitalOcean Improves Developer Onboarding With Wave](<https://devfeed.tech/articles/how-digitalocean-improves-developer-onboarding-with-wave-126466.md>)

Original publisher: [Read original article](<https://amplitude.com/blog/digitalocean-wave>)

Author: Haley Eidem

Published: 2026-11-09T00:00:00Z

Content type: article

Language: en

Sources: [Amplitude](<https://devfeed.tech/sources/amplitude.md>)

Topics: [UI/UX Design](<https://devfeed.tech/topics/ui-ux-design.md>), [Developer experience](<https://devfeed.tech/topics/developer-experience.md>), [Use Cases for Every Cloud Service Model](<https://devfeed.tech/topics/use-cases-for-every-cloud-service-model.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-application](<https://devfeed.tech/tags/ai-application.md>), [ai-inference](<https://devfeed.tech/tags/ai-inference.md>), [ai-products](<https://devfeed.tech/tags/ai-products.md>), [amplitude](<https://devfeed.tech/tags/amplitude.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [cloud-infrastructure](<https://devfeed.tech/tags/cloud-infrastructure.md>), [customer-feedback](<https://devfeed.tech/tags/customer-feedback.md>), [customer-stories](<https://devfeed.tech/tags/customer-stories.md>), [dashboard](<https://devfeed.tech/tags/dashboard.md>), [developer](<https://devfeed.tech/tags/developer.md>), [developer-onboarding](<https://devfeed.tech/tags/developer-onboarding.md>), [digitalocean](<https://devfeed.tech/tags/digitalocean.md>), [experiment](<https://devfeed.tech/tags/experiment.md>), [experiment-design](<https://devfeed.tech/tags/experiment-design.md>), [experimentation](<https://devfeed.tech/tags/experimentation.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [flow](<https://devfeed.tech/tags/flow.md>), [funnel](<https://devfeed.tech/tags/funnel.md>), [onboarding](<https://devfeed.tech/tags/onboarding.md>), [test](<https://devfeed.tech/tags/test.md>)

### AI overview

DigitalOcean used Amplitude Wave across five product areas to turn product data and customer feedback into ranked opportunities, hypotheses, wireframes, experiment plans, and Jira tickets. The team reviewed selected ideas, launched tests with engineering, and monitored results in Amplitude, refining metrics and statistical settings as needed. In onboarding, moving the payment prompt into a banner made teams 3.3% more likely to add a payment method; the result met the configured 80% confidence threshold, so DigitalOcean chose rollout. A dashboard option to hide Product Spotlight left engagement with promoted products essentially unchanged, and the team chose to roll it out. Adding pricing information to the Harness Runtime landing page slightly reduced environment creation, but the team could not conclude the information caused the decline and did not roll it out. Wave reduced PRD work; DigitalOcean plans to test a simpler Harness Runtime flow and says AI product logging and metrics are still being improved.

### Source excerpt

Learn how DigitalOcean uses Amplitude Wave to improve developer onboarding, reduce PRD work, and test changes across cloud and AI products.

## How PixAI lifted publishing nearly 10% with Amplitude Wave

DevFeed: [How PixAI lifted publishing nearly 10% with Amplitude Wave](<https://devfeed.tech/articles/how-pixai-lifted-publishing-nearly-10-with-amplitude-wave-123527.md>)

Original publisher: [Read original article](<https://amplitude.com/blog/pixai-wave-retention>)

Author: Shoin Wolfe

Published: 2026-11-05T00:00:00Z

Content type: article

Language: en

Sources: [Amplitude](<https://devfeed.tech/sources/amplitude.md>)

Topics: [UI/UX Design](<https://devfeed.tech/topics/ui-ux-design.md>), [human computer interaction](<https://devfeed.tech/topics/human-computer-interaction.md>), [Image](<https://devfeed.tech/topics/image.md>), [Tool](<https://devfeed.tech/topics/tool.md>)

Tags: [activation](<https://devfeed.tech/tags/activation.md>), [ai](<https://devfeed.tech/tags/ai.md>), [amplitude](<https://devfeed.tech/tags/amplitude.md>), [analytics](<https://devfeed.tech/tags/analytics.md>), [anime](<https://devfeed.tech/tags/anime.md>), [artwork](<https://devfeed.tech/tags/artwork.md>), [community](<https://devfeed.tech/tags/community.md>), [correlation](<https://devfeed.tech/tags/correlation.md>), [customer-stories](<https://devfeed.tech/tags/customer-stories.md>), [engagement](<https://devfeed.tech/tags/engagement.md>), [experiment](<https://devfeed.tech/tags/experiment.md>), [experimentation](<https://devfeed.tech/tags/experimentation.md>), [growth](<https://devfeed.tech/tags/growth.md>), [hypothesis](<https://devfeed.tech/tags/hypothesis.md>), [image-generation](<https://devfeed.tech/tags/image-generation.md>), [publishing](<https://devfeed.tech/tags/publishing.md>), [retention](<https://devfeed.tech/tags/retention.md>)

### AI overview

PixAI's Amplitude Wave analysis found that publishing artwork correlated with retention. The team adapted Wave's suggestion to prompt publishing after image generation: when users ran out of generation credits, a tooltip directed them to the Missions tab, where publishing daily artwork earns credits. In an A/B test, Missions opens rose 76.7%, publishing nearly 10%, and Day 1 retention 3% over control. The team credits Wave with identifying the behavior and opportunity, while PixAI chose how to apply that insight using its existing credit system. The excerpt also reports that adding qualitative product context made Wave's visual mockups more recognizable and easier to assess.

### Source excerpt

Discover how PixAI used Amplitude Wave to turn a retention insight into a tooltip that increased publishing nearly 10%.

## Get Your Ecommerce Data Ready Before Holiday Traffic Arrives

DevFeed: [Get Your Ecommerce Data Ready Before Holiday Traffic Arrives](<https://devfeed.tech/articles/get-your-ecommerce-data-ready-before-holiday-traffic-arrives-121115.md>)

Original publisher: [Read original article](<https://amplitude.com/blog/holiday-ecommerce-data>)

Author: Michele Morales

Published: 2026-11-04T00:00:00Z

Content type: tutorial

Language: en

Sources: [Amplitude](<https://devfeed.tech/sources/amplitude.md>)

Topics: [product analytics](<https://devfeed.tech/topics/product-analytics.md>), [data](<https://devfeed.tech/topics/data.md>), [dashboards](<https://devfeed.tech/topics/dashboards.md>)

Tags: [amplitude](<https://devfeed.tech/tags/amplitude.md>), [arrays](<https://devfeed.tech/tags/arrays.md>), [best-practices](<https://devfeed.tech/tags/best-practices.md>), [configure](<https://devfeed.tech/tags/configure.md>), [data](<https://devfeed.tech/tags/data.md>), [ecommerce](<https://devfeed.tech/tags/ecommerce.md>), [events](<https://devfeed.tech/tags/events.md>), [funnels](<https://devfeed.tech/tags/funnels.md>), [holiday](<https://devfeed.tech/tags/holiday.md>), [hub](<https://devfeed.tech/tags/hub.md>), [product](<https://devfeed.tech/tags/product.md>), [shopping](<https://devfeed.tech/tags/shopping.md>), [traffic](<https://devfeed.tech/tags/traffic.md>)

### AI overview

Trustworthy ecommerce analysis during holiday traffic depends on validating tracking and configuration before the sale. Test shopping journeys across devices and payment paths, reconcile purchases and revenue with the order system, and check for missing or duplicate events and identifier gaps. Verify purchase product arrays and item properties; validate item-level revenue separately from order-level revenue, and use the order system if the calculation cannot be confirmed. Configure discovery context and persisted properties with explicit attribution rules, keeping onsite discovery distinct from acquisition channel. Then validate Amplitude's Purchase by Product and Product Discovery views against known journeys, and test funnel alerts, delivery delay, and escalation ownership. Server-side or hybrid tracking needs checks for identifiers, properties, retries, deduplication, and whether browser or discovery context is available. The excerpt recommends testing configuration changes outside production and scheduling untested structural changes early enough to validate.

### Source excerpt

Prepare your ecommerce data for holiday shopping. Validate events, product arrays, attribution, and funnels, then configure your Amplitude ecommerce hub.

## Amplitude + GitHub Agents: Closing the Product Learning Loop

DevFeed: [Amplitude + GitHub Agents: Closing the Product Learning Loop](<https://devfeed.tech/articles/amplitude-github-agents-closing-the-product-learning-loop-90087.md>)

Original publisher: [Read original article](<https://amplitude.com/blog/amplitude-github-learning-loop>)

Author: Christina Nguyen

Published: 2026-10-19T00:00:00Z

Content type: article

Language: en

Sources: [Amplitude](<https://devfeed.tech/sources/amplitude.md>)

Topics: [product-experimentation](<https://devfeed.tech/topics/product-experimentation.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [GitHub Copilot](<https://devfeed.tech/topics/github-copilot.md>), [product analytics](<https://devfeed.tech/topics/product-analytics.md>)

Tags: [activation](<https://devfeed.tech/tags/activation.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [amplitude](<https://devfeed.tech/tags/amplitude.md>), [analytics](<https://devfeed.tech/tags/analytics.md>), [behavior](<https://devfeed.tech/tags/behavior.md>), [best-practices](<https://devfeed.tech/tags/best-practices.md>), [copilot](<https://devfeed.tech/tags/copilot.md>), [experiment](<https://devfeed.tech/tags/experiment.md>), [feature](<https://devfeed.tech/tags/feature.md>), [github](<https://devfeed.tech/tags/github.md>), [github-copilot](<https://devfeed.tech/tags/github-copilot.md>), [github-issue](<https://devfeed.tech/tags/github-issue.md>), [guardrails](<https://devfeed.tech/tags/guardrails.md>), [ideas](<https://devfeed.tech/tags/ideas.md>), [impact](<https://devfeed.tech/tags/impact.md>), [integration](<https://devfeed.tech/tags/integration.md>), [product](<https://devfeed.tech/tags/product.md>)

### AI overview

The article describes a product learning loop connecting Amplitude Wave, GitHub Copilot, and Statsig. Wave uses behavioral analytics and session replays to identify onboarding friction and propose a fix; Copilot turns the proposal into a pull request for engineering review; and Statsig feature gates and randomized experiments measure the change before broader rollout.

### Source excerpt

How teams are building the right thing at AI speed with GitHub Copilot, Amplitude Wave, and Statsig

## Lessons from consolidating our MCP server

DevFeed: [Lessons from consolidating our MCP server](<https://devfeed.tech/articles/lessons-from-consolidating-our-mcp-server-84743.md>)

Original publisher: [Read original article](<https://amplitude.com/blog/lessons-from-consolidating-our-mcp-server>)

Author: Chanaka Perera

Published: 2026-10-06T00:00:00Z

Content type: article

Language: en

Sources: [Amplitude](<https://devfeed.tech/sources/amplitude.md>)

Topics: [MSP MCP](<https://devfeed.tech/topics/msp-mcp.md>), [Multi-step AI processes](<https://devfeed.tech/topics/multi-step-ai-processes.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [Page Speed Optimization](<https://devfeed.tech/topics/page-speed-optimization.md>)

Tags: [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-tools](<https://devfeed.tech/tags/ai-tools.md>), [composability](<https://devfeed.tech/tags/composability.md>), [context-window](<https://devfeed.tech/tags/context-window.md>), [cost](<https://devfeed.tech/tags/cost.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [mcp-server](<https://devfeed.tech/tags/mcp-server.md>), [perspectives](<https://devfeed.tech/tags/perspectives.md>)

### AI overview

Amplitude redesigned its MCP server after a catalog of 96 endpoint-oriented tools created high context costs, overlap, and incomplete multi-call workflows. It grouped tools around objects and user outcomes, moved detailed instructions into on-demand skills, added UI-based confirmation for sensitive actions, and rolled out changes behind feature flags. Monitoring showed high recovery after errors and customer retention of 67% at one week, 59% at four weeks, and 50% at eight weeks among external users.

### Source excerpt

Learn how Amplitude redesigned its MCP server to reduce context bloat, consolidate tools, and help AI agents complete tasks in fewer calls.

## What AI engineers do in the age of agentic code

DevFeed: [What AI engineers do in the age of agentic code](<https://devfeed.tech/articles/what-ai-engineers-do-in-the-age-of-agentic-code-84758.md>)

Original publisher: [Read original article](<https://amplitude.com/blog/what-ai-engineers-do>)

Author: Adam Bonefeste

Published: 2026-10-01T00:00:00Z

Content type: article

Language: en

Sources: [Amplitude](<https://devfeed.tech/sources/amplitude.md>)

Topics: [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [Code review](<https://devfeed.tech/topics/code-review.md>), [Product Management](<https://devfeed.tech/topics/product-management.md>)

Tags: [accountability](<https://devfeed.tech/tags/accountability.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [ai](<https://devfeed.tech/tags/ai.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [build](<https://devfeed.tech/tags/build.md>), [coaching](<https://devfeed.tech/tags/coaching.md>), [coding](<https://devfeed.tech/tags/coding.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [perspectives](<https://devfeed.tech/tags/perspectives.md>)

### AI overview

AI engineers are increasingly directing coding agents, reviewing their output, and remaining accountable for product quality. The article describes how this work shifts attention toward code review, prioritization, evaluation, and trust, while juggling parallel agent tasks can fragment focus and leave work unfinished. Through four Amplitude examples, it shows varied roles in building and improving AI products and workflows.

### Source excerpt

AI agents write most of the code behind modern products. How can AI engineers evolve their day-to-day work to improve product trust?

## An analysis of Jev: Faster and cheaper, but watch the accuracy

DevFeed: [An analysis of Jev: Faster and cheaper, but watch the accuracy](<https://devfeed.tech/articles/an-analysis-of-jev-faster-and-cheaper-but-watch-the-accuracy-84742.md>)

Original publisher: [Read original article](<https://amplitude.com/blog/jev-analysis>)

Author: Vinay Goel and Ram Soma

Published: 2026-09-28T00:00:00Z

Content type: article

Language: en

Sources: [Amplitude](<https://devfeed.tech/sources/amplitude.md>)

Topics: [enhancing AI model accuracy](<https://devfeed.tech/topics/enhancing-ai-model-accuracy.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [product-experimentation](<https://devfeed.tech/topics/product-experimentation.md>)

Tags: [ai-analytics](<https://devfeed.tech/tags/ai-analytics.md>), [ai-implementation](<https://devfeed.tech/tags/ai-implementation.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [decision-models](<https://devfeed.tech/tags/decision-models.md>), [perspectives](<https://devfeed.tech/tags/perspectives.md>)

### AI overview

The article examines decision models such as Jev, which produce typed decisions quickly and cheaply, and reviews benchmark evidence about their accuracy. In a synthetic product analytics benchmark, Jev caught every meaningful chart but escalated more benign charts than the best general-purpose models. The authors argue that confidence-based cascades alone can miss confident errors and recommend evaluating model decisions against subsequent user behavior captured in product data.

### Source excerpt

Decision models show a lot of promise. We reviewed benchmark tests and ran our own to better understand their strengths, shortcomings, and how to improve their accuracy.

## How Amplitude AI Context helps agents answer analytics questions using team definitions

DevFeed: [How Amplitude AI Context helps agents answer analytics questions using team definitions](<https://devfeed.tech/articles/your-agent-isn-t-broken-it-s-guessing-84719.md>)

Original publisher: [Read original article](<https://amplitude.com/blog/ai-context-configuration>)

Author: Michele Morales

Published: 2026-09-23T00:00:00Z

Content type: tutorial

Language: en

Sources: [Amplitude](<https://devfeed.tech/sources/amplitude.md>)

Topics: [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [AI Context Switching](<https://devfeed.tech/topics/ai-context-switching.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [amplitude](<https://devfeed.tech/tags/amplitude.md>), [best-practices](<https://devfeed.tech/tags/best-practices.md>), [context](<https://devfeed.tech/tags/context.md>)

### AI overview

Amplitude's AI Context feature lets teams set organization-wide definitions and narrower project rules so its agent can answer analytics questions using agreed-upon terms. The article advises keeping project rules consistent with organization definitions and reviewing context periodically as the product changes.

### Source excerpt

When an AI agent gets a query wrong, it's rarely a model bug. It's a context gap. Setting up AI Context closes it for good.

## Amplitude reduces MCP tool catalog and adds a developer CLI

DevFeed: [Amplitude reduces MCP tool catalog and adds a developer CLI](<https://devfeed.tech/articles/bring-headless-amplitude-where-you-work-84737.md>)

Original publisher: [Read original article](<https://amplitude.com/blog/headless-amplitude>)

Author: Eric Kim

Published: 2026-09-16T00:00:00Z

Content type: article

Language: en

Sources: [Amplitude](<https://devfeed.tech/sources/amplitude.md>)

Topics: [Developer experience](<https://devfeed.tech/topics/developer-experience.md>), [Kontent.ai](<https://devfeed.tech/topics/kontent-ai.md>)

Tags: [chatgpt](<https://devfeed.tech/tags/chatgpt.md>), [claude](<https://devfeed.tech/tags/claude.md>), [cli](<https://devfeed.tech/tags/cli.md>), [codex](<https://devfeed.tech/tags/codex.md>), [cursor](<https://devfeed.tech/tags/cursor.md>), [developer](<https://devfeed.tech/tags/developer.md>), [headless](<https://devfeed.tech/tags/headless.md>), [inside-amplitude](<https://devfeed.tech/tags/inside-amplitude.md>), [service](<https://devfeed.tech/tags/service.md>), [service-accounts](<https://devfeed.tech/tags/service-accounts.md>), [token](<https://devfeed.tech/tags/token.md>)

### AI overview

Amplitude describes updates to its MCP server, including consolidating more than 100 tools into a smaller catalog that typically loads about 40, and says task completion matched or improved across more than 80 paired test scenarios. It also introduces a developer CLI and service accounts for programmatic access, making product context available through AI clients and terminal workflows.

### Source excerpt

Between tool consolidation for large reductions in token counts, a new developer CLI, and Service Accounts, using Amplitude in headless mode is easier than ever.

## Amplitude climbs to #3 in G2 Digital Analytics Momentum

DevFeed: [Amplitude climbs to #3 in G2 Digital Analytics Momentum](<https://devfeed.tech/articles/amplitude-climbs-to-3-in-g2-digital-analytics-momentum-84733.md>)

Original publisher: [Read original article](<https://amplitude.com/blog/g2-fall-2026-digital-analytics>)

Author: Ashlyn Warblow

Published: 2026-09-15T00:00:00Z

Content type: article

Language: en

Sources: [Amplitude](<https://devfeed.tech/sources/amplitude.md>)

Topics: [product analytics](<https://devfeed.tech/topics/product-analytics.md>), [Google Analytics](<https://devfeed.tech/topics/google-analytics.md>), [experiments](<https://devfeed.tech/topics/experiments.md>)

Tags: [acquisition](<https://devfeed.tech/tags/acquisition.md>), [amplitude](<https://devfeed.tech/tags/amplitude.md>), [analytics](<https://devfeed.tech/tags/analytics.md>), [behavioral-analysis](<https://devfeed.tech/tags/behavioral-analysis.md>), [conversion](<https://devfeed.tech/tags/conversion.md>), [customer-stories](<https://devfeed.tech/tags/customer-stories.md>), [dashboards](<https://devfeed.tech/tags/dashboards.md>), [data](<https://devfeed.tech/tags/data.md>), [data-product-manager](<https://devfeed.tech/tags/data-product-manager.md>)

### AI overview

Amplitude reports its Fall 2026 G2 rankings and presents customer accounts describing why they switched from Google Analytics or Adobe Analytics. The article emphasizes self-serve behavioral analytics, including funnels, cohorts and retention, while noting tradeoffs such as event setup, rebuilding standard reports and a learning curve.

### Source excerpt

See how Amplitude climbed to #3 in Digital Analytics momentum in G2's Fall 2026 reports, and what real customers say drove their switch to Amplitude.

## Should I install the Amplitude SDK?

DevFeed: [Should I install the Amplitude SDK?](<https://devfeed.tech/articles/should-i-install-the-amplitude-sdk-84722.md>)

Original publisher: [Read original article](<https://amplitude.com/blog/amplitude-sdk-or-not>)

Author: Sean Kilcullen

Published: 2026-09-15T00:00:00Z

Content type: article

Language: en

Sources: [Amplitude](<https://devfeed.tech/sources/amplitude.md>)

Topics: [SDK](<https://devfeed.tech/topics/sdk.md>), [streaming data analytics](<https://devfeed.tech/topics/streaming-data-analytics.md>)

Tags: [ai-analytics](<https://devfeed.tech/tags/ai-analytics.md>), [amplitude](<https://devfeed.tech/tags/amplitude.md>), [data-platform](<https://devfeed.tech/tags/data-platform.md>), [perspectives](<https://devfeed.tech/tags/perspectives.md>), [sdk](<https://devfeed.tech/tags/sdk.md>)

### AI overview

The article compares Amplitude SDK collection with warehouse imports and other event ingestion paths. It explains that the SDK can capture interaction-level behavior for features such as autocapture, Session Replay, exposure tracking and in-product experiments, while warehouse imports can suit teams focused on reconciled business records or constrained by governance requirements. It recommends considering the capabilities and constraints a team needs before choosing an ingestion setup.

### Source excerpt

Deciding whether the Amplitude SDK is right for you? Compare SDK to warehouse ingestion, see what each one captures, and learn when a hybrid setup fits best.

## Automating Marketing Request Triage with Asana and Claude

DevFeed: [Automating Marketing Request Triage with Asana and Claude](<https://devfeed.tech/articles/i-was-the-bottleneck-84724.md>)

Original publisher: [Read original article](<https://amplitude.com/blog/automating-request-triage>)

Author: Chelsie Cauthon

Published: 2026-09-10T00:00:00Z

Content type: article

Language: en

Sources: [Amplitude](<https://devfeed.tech/sources/amplitude.md>)

Topics: [workflow automation](<https://devfeed.tech/topics/workflow-automation.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [human review](<https://devfeed.tech/topics/human-review.md>)

Tags: [ai-teammates](<https://devfeed.tech/tags/ai-teammates.md>), [asana](<https://devfeed.tech/tags/asana.md>), [automation](<https://devfeed.tech/tags/automation.md>), [claude](<https://devfeed.tech/tags/claude.md>), [marketing](<https://devfeed.tech/tags/marketing.md>), [perspectives](<https://devfeed.tech/tags/perspectives.md>), [review](<https://devfeed.tech/tags/review.md>), [triage](<https://devfeed.tech/tags/triage.md>), [workflow](<https://devfeed.tech/tags/workflow.md>)

### AI overview

Amplitude's marketing operations team automated request scoping and triage with Asana AI Teammates and a Claude skill, allowing requests to be processed across time zones. After comparing the tools, the team chose the Claude skill because corrections were easier to make. A human still reviews the completed work.

### Source excerpt

Amplitude's marketing ops team automated request triage using Asana AI Teammates and Claude, cutting a three-person workflow to a single QA review.

## How semantic data context helps AI agents answer business questions accurately

DevFeed: [How semantic data context helps AI agents answer business questions accurately](<https://devfeed.tech/articles/your-agents-are-only-as-good-as-your-data-context-84717.md>)

Original publisher: [Read original article](<https://amplitude.com/blog/ai-agents-need-good-context>)

Author: Michele Morales

Published: 2026-09-04T00:00:00Z

Content type: article

Language: en

Sources: [Amplitude](<https://devfeed.tech/sources/amplitude.md>)

Topics: [context-architecture](<https://devfeed.tech/topics/context-architecture.md>), [AI-Ready Data](<https://devfeed.tech/topics/ai-ready-data.md>), [human review](<https://devfeed.tech/topics/human-review.md>), [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [data](<https://devfeed.tech/topics/data.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [amplitude](<https://devfeed.tech/tags/amplitude.md>), [certification](<https://devfeed.tech/tags/certification.md>), [data](<https://devfeed.tech/tags/data.md>), [data-context](<https://devfeed.tech/tags/data-context.md>), [data-lineage](<https://devfeed.tech/tags/data-lineage.md>), [data-team](<https://devfeed.tech/tags/data-team.md>), [data-teams](<https://devfeed.tech/tags/data-teams.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [dbt](<https://devfeed.tech/tags/dbt.md>), [perspectives](<https://devfeed.tech/tags/perspectives.md>)

### AI overview

AI agents need business context to interpret data correctly. The article explains how a semantic layer can define metrics, events, terminology, data quality, lineage, and ownership, and recommends limiting agents to focused datasets and having people review their answers. It describes Amplitude's work preparing marketing attribution data for AI and reports that its agent answered questions correctly 80 to 90 percent of the time after building a semantic layer.

### Source excerpt

Humans can recognize when something doesn't smell right. AI can't without context. Good data context is the answer.

## The New Trust Economy in Financial Services

DevFeed: [The New Trust Economy in Financial Services](<https://devfeed.tech/articles/the-new-trust-economy-in-financial-services-84753.md>)

Original publisher: [Read original article](<https://amplitude.com/blog/trust-economy-financial-services>)

Author: Mark Drasutis

Published: 2026-09-02T00:00:00Z

Content type: article

Language: en

Sources: [Amplitude](<https://devfeed.tech/sources/amplitude.md>)

Topics: [API Economy](<https://devfeed.tech/topics/api-economy.md>), [digital experience monitoring](<https://devfeed.tech/topics/digital-experience-monitoring.md>)

Tags: [amplitude](<https://devfeed.tech/tags/amplitude.md>), [analytics](<https://devfeed.tech/tags/analytics.md>), [banking](<https://devfeed.tech/tags/banking.md>), [digital-experience](<https://devfeed.tech/tags/digital-experience.md>), [financial-services](<https://devfeed.tech/tags/financial-services.md>), [perspectives](<https://devfeed.tech/tags/perspectives.md>), [trust](<https://devfeed.tech/tags/trust.md>)

### AI overview

The article argues that financial institutions now earn customer trust through their digital product experiences, with behavior observed and addressed continuously. Examples from Salt Bank, Xapo Bank, and ACKO describe changes to account activation, identity verification, and insurance offers. It says institutions can use analytics and governed experimentation to find customer friction, improve support and onboarding, and respond to customer needs.

### Source excerpt

Trust used to be a one-way decision: banks judged consumers, and consumers had little say. That direction has flipped, and most institutions haven't noticed.

## How Amplitude Protects AI Agent Traces with Access Controls and Privacy Modes

DevFeed: [How Amplitude Protects AI Agent Traces with Access Controls and Privacy Modes](<https://devfeed.tech/articles/how-to-secure-ai-agent-traces-without-losing-the-signal-84716.md>)

Original publisher: [Read original article](<https://amplitude.com/blog/agent-data-security>)

Author: Nhi Dao

Published: 2026-08-28T00:00:00Z

Content type: article

Language: en

Sources: [Amplitude](<https://devfeed.tech/sources/amplitude.md>)

Topics: [rbac](<https://devfeed.tech/topics/rbac.md>), [ai observability](<https://devfeed.tech/topics/ai-observability.md>), [human in the loop agent](<https://devfeed.tech/topics/human-in-the-loop-agent.md>), [telemetry](<https://devfeed.tech/topics/telemetry.md>)

Tags: [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [best-practices](<https://devfeed.tech/tags/best-practices.md>), [customer-trust](<https://devfeed.tech/tags/customer-trust.md>), [evals](<https://devfeed.tech/tags/evals.md>), [privacy](<https://devfeed.tech/tags/privacy.md>), [redaction](<https://devfeed.tech/tags/redaction.md>)

### AI overview

Amplitude explains how Agent Analytics protects agent traces with role-based access, configurable privacy modes and PII redaction. It describes how teams can retain evaluation and quality signals while limiting sensitive text, and how permissions, audit records, regional data handling and AI workflows affect trace security.

### Source excerpt

Role-based access and privacy redaction are on by default. Take advantage of enterprise-grade controls when sending traces to Amplitude Agent Analytics.

## Connecting agent performance to product outcomes

DevFeed: [Connecting agent performance to product outcomes](<https://devfeed.tech/articles/connecting-agent-performance-to-product-outcomes-84730.md>)

Original publisher: [Read original article](<https://amplitude.com/blog/connecting-agent-performance-to-product-outcomes>)

Author: Darshil Gandhi

Published: 2026-08-20T00:00:00Z

Content type: article

Language: en

Sources: [Amplitude](<https://devfeed.tech/sources/amplitude.md>)

Topics: [product analytics](<https://devfeed.tech/topics/product-analytics.md>), [agent observability](<https://devfeed.tech/topics/agent-observability.md>), [AI agent hallucinations](<https://devfeed.tech/topics/ai-agent-hallucinations.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [agent](<https://devfeed.tech/tags/agent.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-evaluations](<https://devfeed.tech/tags/ai-evaluations.md>), [analytics](<https://devfeed.tech/tags/analytics.md>), [best-practices](<https://devfeed.tech/tags/best-practices.md>), [product](<https://devfeed.tech/tags/product.md>)

### AI overview

Amplitude describes Agent Analytics, a product for evaluating AI agent sessions in production and connecting quality signals to business outcomes such as conversion, retention, and monetization. The article covers built-in evaluations, conversation clustering, automated monitoring agents, and performance improvements for large datasets.

### Source excerpt

Observe what users ask your AI agent, evaluate where it fails and what those failures cost your business. Agent Analytics is now available to all customers.

## Verification loops in software factories: What PMs need to know

DevFeed: [Verification loops in software factories: What PMs need to know](<https://devfeed.tech/articles/verification-loops-in-software-factories-what-pms-need-to-know-84755.md>)

Original publisher: [Read original article](<https://amplitude.com/blog/verification-loops>)

Author: Adam Bonefeste

Published: 2026-08-19T00:00:00Z

Content type: article

Language: en

Sources: [Amplitude](<https://devfeed.tech/sources/amplitude.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 Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [engineering-culture](<https://devfeed.tech/topics/engineering-culture.md>)

Tags: [ai-evals](<https://devfeed.tech/tags/ai-evals.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [analytics](<https://devfeed.tech/tags/analytics.md>), [business](<https://devfeed.tech/tags/business.md>), [coding-agent](<https://devfeed.tech/tags/coding-agent.md>), [data](<https://devfeed.tech/tags/data.md>), [loops](<https://devfeed.tech/tags/loops.md>), [perspectives](<https://devfeed.tech/tags/perspectives.md>)

### AI overview

The article explains verification loops used by AI agents during software development, including separate graders that assess whether an output meets a goal. It distinguishes those build checks from a post-ship optimize loop, where product managers use real user behavior and experiments to judge whether changes improve product metrics and user experience.

### Source excerpt

Learn what verification loops check inside a software factory, why they can't tell you if a change moved your metric, and the post-ship loop PMs need to own.

## The hidden cost of a bad AI answer

DevFeed: [The hidden cost of a bad AI answer](<https://devfeed.tech/articles/the-hidden-cost-of-a-bad-ai-answer-84727.md>)

Original publisher: [Read original article](<https://amplitude.com/blog/cashbook-ai-failure-rate>)

Author: Nikhil Mishra

Published: 2026-08-19T00:00:00Z

Content type: article

Language: en

Sources: [Amplitude](<https://devfeed.tech/sources/amplitude.md>)

Topics: [DORA change failure rate](<https://devfeed.tech/topics/dora-change-failure-rate.md>), [LLM observability](<https://devfeed.tech/topics/llm-observability.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>)

Tags: [adoption](<https://devfeed.tech/tags/adoption.md>), [ai](<https://devfeed.tech/tags/ai.md>), [amplitude](<https://devfeed.tech/tags/amplitude.md>), [analytics](<https://devfeed.tech/tags/analytics.md>), [cost](<https://devfeed.tech/tags/cost.md>), [customer-stories](<https://devfeed.tech/tags/customer-stories.md>), [failure](<https://devfeed.tech/tags/failure.md>), [retention](<https://devfeed.tech/tags/retention.md>), [transcripts](<https://devfeed.tech/tags/transcripts.md>)

### AI overview

CashBook describes building an AI agent that answers questions about business transaction data and FAQs, then evaluating its performance with session-level analytics and a Failure Rate metric. After usage declined and failure rates remained high, the company held back a wider rollout. Its early data showed a 15-point gap in week-four retention between users with failed sessions and those without, though the sample was thin.

### Source excerpt

See how CashBook replaced hand-read transcripts with a measurable AI failure rate, and why one bad first answer cost 15 points of retention in four weeks.

## Your AI chat box isn't a strategy. Where you put it is.

DevFeed: [Your AI chat box isn't a strategy. Where you put it is.](<https://devfeed.tech/articles/your-ai-chat-box-isn-t-a-strategy-where-you-put-it-is-84718.md>)

Original publisher: [Read original article](<https://amplitude.com/blog/ai-chat-box-tests>)

Author: Amy Lin

Published: 2026-08-18T00:00:00Z

Content type: article

Language: en

Sources: [Amplitude](<https://devfeed.tech/sources/amplitude.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-experiments](<https://devfeed.tech/topics/ai-experiments.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>)

Tags: [adoption](<https://devfeed.tech/tags/adoption.md>), [agent](<https://devfeed.tech/tags/agent.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-strategy](<https://devfeed.tech/tags/ai-strategy.md>), [amplitude](<https://devfeed.tech/tags/amplitude.md>), [best-practices](<https://devfeed.tech/tags/best-practices.md>), [experiment](<https://devfeed.tech/tags/experiment.md>), [strategy](<https://devfeed.tech/tags/strategy.md>)

### AI overview

Amplitude describes experiments on where to place its Global Agent AI chat experience across onboarding, the home page, and chart and dashboard workflows. The tests found that prompts tailored to users' roles, a chat-first home page, and entry points embedded in existing workflows increased engagement or adoption. The article recommends testing how a chat interface fits users' intentions and behavior, then tracking the results.

### Source excerpt

How does Amplitude understand what users want from an AI chat box? Here are the biggest takeaways from our early tests.

## From context to intelligence: Building self-improving products in banking and insurance

DevFeed: [From context to intelligence: Building self-improving products in banking and insurance](<https://devfeed.tech/articles/from-context-to-intelligence-building-self-improving-products-in-banking-and-insurance-84731.md>)

Original publisher: [Read original article](<https://amplitude.com/blog/context-to-intelligence-self-improving-products-banking-insurance>)

Author: Mark Drasutis

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

Content type: article

Language: en

Sources: [Amplitude](<https://devfeed.tech/sources/amplitude.md>)

Topics: [product analytics](<https://devfeed.tech/topics/product-analytics.md>), [product mindset](<https://devfeed.tech/topics/product-mindset.md>), [personalization](<https://devfeed.tech/topics/personalization.md>)

Tags: [amplitude](<https://devfeed.tech/tags/amplitude.md>), [banking](<https://devfeed.tech/tags/banking.md>), [insurance](<https://devfeed.tech/tags/insurance.md>), [perspectives](<https://devfeed.tech/tags/perspectives.md>)

### AI overview

The article describes a continuous product improvement loop for banking and insurance: interpret behavioral and transactional data as customer context, then use those insights to adjust experiences such as question order, messaging, and cross-sell offers. It illustrates the approach with ACKO examples and argues for stronger oversight near regulated product terms and risk decisions.

### Source excerpt

Why the next generation of financial products will learn from every customer they serve

[Next page](<https://devfeed.tech/sources/amplitude.md?cursor=WyIyMDI2LTA4LTE3VDAwOjAwOjAwKzAwOjAwIiwgIjY1Y2FlZDUxLTY1OGQtNGZmYy1hMDUyLTVmOWViY2QzYjJmOCJd>)