Customer SupportOctopus Energy
Octopus Energy's AI email assistant Arlo scored higher satisfaction than human replies
76% customer satisfaction for AI replies vs 72% for comparable human replies, on ~8,000 emails a week (4% of UK customer emails).
What AI agents are really doing in production.
A searchable directory of real-world AI agent use cases. Every entry links to its evidence, says who reported the result, and lists the caveats.
- Use cases
- 35
- Organizations
- 33
- Cited sources
- 63
- Categories
- 11
35 of 35 use cases
Software EngineeringStripe
Stripe's Minions coding agents produce 1,000+ merged pull requests every week
More than a thousand pull requests merged each week are fully agent-produced and human-reviewed.
Sales & MarketingAnthropic
Anthropic's growth marketer cut ad creation from 30 minutes to 30 seconds with Claude Code
Work that took about 30 minutes per ad now takes about 30 seconds; the plugin can make up to 100 ad variations at once.
Software EngineeringSpotify
Spotify's Honk background agent merges fleet-wide code migrations: 1,500+ PRs and counting
1,500+ merged AI-generated PRs; 1,000 merged PRs took three months at first and about ten days later on.
Sales & MarketingAmazon
Amazon says its Rufus shopping assistant is on track for $10B+ in extra yearly sales
Amazon expects over $10B in annualized incremental sales; shoppers who used Rufus were 60% more likely to buy.
Company reportedRufus
Finance & OperationsBNY
BNY runs 100+ AI 'digital employees' with their own logins and human managers
Over 100 digital employees in production by October 2025, later reported as 130+, each with a human supervisor.
SecurityGoogle DeepMind
Google DeepMind's CodeMender agent upstreamed 72 security fixes to open-source projects
72 security fixes upstreamed to open-source projects in six months, including projects as large as 4.5 million lines of code.
Software EngineeringAider (open source)
Aider, the open-source coding agent, writes most of its own code
Aider's release notes report that Aider wrote up to 88% of the code in a release (v0.86.0, August 2025).
Company reportedAider
Customer SupportSalesforce
Salesforce runs its own support on Agentforce and cut support headcount from ~9,000 to ~5,000
About 1.5M customer conversations handled by agents, with CSAT about the same as humans; support headcount went from ~9,000 to ~5,000.
Company reportedAgentforce
Software EngineeringGoldman Sachs
Goldman Sachs pilots Devin as an AI engineer next to its 12,000 developers
Pilot started with plans for hundreds of instances; the CIO expects 3–4x developer output on routine code updates.
Press reportDevin
Finance & OperationsRamp
Ramp's policy agent reviews expenses against company policy for 1,000+ finance teams
Used by 1,000+ finance teams within six months; Ramp claims 99% approval accuracy and 7x more out-of-policy spend caught.
Software EngineeringCloudflare
Cloudflare built an OAuth 2.1 library with Claude and published the prompts in git
A working OAuth 2.1 provider library for Cloudflare Workers, written mostly by Claude and reviewed by Cloudflare engineers.
IndependentClaude
SecurityXBOW
XBOW's autonomous pentesting agent reached #1 on HackerOne's US leaderboard
#1 on the HackerOne US leaderboard, with 1,000+ reports in a few months and 130+ confirmed and fixed by program owners.
Press reportXBOW
Software EngineeringAirbnb
Airbnb migrated 3,500 test files with an LLM pipeline in 6 weeks instead of 1.5 years
~3,500 test files migrated in 6 weeks; about 97% fully automated and the rest finished by hand.
Company reportedLLM pipeline (custom)
ResearchSakana AI
Sakana's AI Scientist-v2 wrote a paper that passed peer review at an ICLR workshop
One of three fully AI-generated submissions cleared the acceptance bar at the ICBINB workshop (scores 6, 7, 6).
Research paperThe AI Scientist-v2
ResearchGoogle Research & Imperial College London
Google's AI co-scientist proposed the same superbug hypothesis an Imperial College team spent years on
The system's top hypothesis matched the Imperial team's unpublished finding about how bacteria spread resistance genes.
Customer SupportLyft
Lyft cut average support resolution time by 87% with a Claude-based assistant
Average resolution time fell by more than 87%, with thousands of requests resolved per day (company claim).
Software EngineeringGoogle
Google uses LLMs for internal code migrations and reports about 50% less migration time
Across 39 migrations, about 74% of code changes were LLM-generated; developers estimated a 50% cut in total migration time.
Research paperGemini (internal)
HR & RecruitingIBM
IBM's AskHR agent resolves 94% of common HR questions without a person
94% containment of common questions, 75% fewer HR support tickets since 2016, and a 40% cut in HR operating costs over four years.
Company reportedAskHR (watsonx Orchestrate)
Customer SupportIntercom (and its customers)
Intercom's Fin AI agent resolves about two-thirds of support conversations on average
Average resolution rate of 66–67% across about 6,000 customers, up from about 51% at launch.
Internal ToolsMcKinsey & Company
McKinsey's Lilli platform is used regularly by over 70% of the firm's staff
More than 70% of the firm uses Lilli regularly, with millions of prompts answered (company figures).
Company reportedLilli (internal)
Software EngineeringRakuten
Rakuten engineer let Claude Code work alone for 7 hours on a vLLM feature
Seven hours of mostly autonomous coding in one run. Rakuten reports 99.9% numerical accuracy versus the reference method.
Vendor case studyClaude Code
Sales & MarketingVercel
Vercel's lead agent took inbound qualification from a 10-person team to about one person
Inbound SDR work went from about 10 people to 1 plus a part-time person; the agent costs about $5,000 a year to run (as reported).
Press reportCustom agent (Vercel AI SDK)
SecurityGoogle (Project Zero & DeepMind)
Google's Big Sleep agent found an exploitable SQLite bug that fuzzing missed
Found a previously unknown, exploitable memory-safety bug in SQLite; developers patched it the same day, before any release.
HR & RecruitingLinkedIn
LinkedIn's Hiring Assistant agent finds candidates and drafts outreach for recruiters
Launched to charter customers including AMD, Canva, Siemens, and Zurich Insurance, aiming at the 20+ hours a week recruiters spend on admin.
Company reportedLinkedIn Hiring Assistant
Internal ToolsUber
Uber's Genie answers on-call questions in Slack and saved ~13,000 engineering hours
70,000+ questions answered across 154 Slack channels, with an estimated 13,000 engineering hours saved.
Data & AnalyticsUber
Uber's QueryGPT turns plain-English questions into SQL, cutting query time from ~10 to ~3 minutes
Uber estimates a query that took about 10 minutes to write by hand now takes about 3 minutes; the limited release reached ~300 daily active users.
Software EngineeringAmazon
Amazon upgraded 30,000 internal apps to Java 17 with Amazon Q Developer
30,000 apps upgraded. Amazon estimates 4,500 developer-years saved and $260M a year from performance gains.
Company reportedAmazon Q Developer
HealthcareKaiser Permanente
Kaiser Permanente rolled out Abridge ambient AI notes to 24,000+ doctors
One of the largest generative AI rollouts in healthcare: 24,000+ physicians across ~40 hospitals and 600+ offices.
Press reportAbridge
Finance & OperationsMorgan Stanley
Morgan Stanley's Debrief agent takes notes in advisor meetings and drafts the follow-up email
Rolled out to the firm's financial advisors in 2024; the firm cites about 30 minutes saved per client meeting (testimonial).
Customer SupportKlarna
Klarna's AI assistant took two-thirds of support chats in its first month
2.3M conversations in the first month, about two-thirds of all service chats, the work of roughly 700 full-time agents (company claim).
Company reportedOpenAI GPT-4
Customer SupportDoorDash
DoorDash built a voice AI agent for Dasher support calls with answers in under 2.5 seconds
A voice agent ready for live testing in about two months, answering in 2.5 seconds or less, with 50x more testing capacity.
Software EngineeringNubank
Nubank used Devin to split an 8-year-old ETL monolith into sub-modules
Cognition reports 8–12x engineering-time efficiency and over 20x cost savings on the data-class migrations.
Vendor case studyDevin
Data & AnalyticsPinterest
Pinterest's text-to-SQL agent helps analysts find tables and write queries 35% faster
Pinterest reports 35% faster task completion for SQL writing, and first-shot acceptance rising from 20% to over 40%.
LegalA&O Shearman (Allen & Overy)
Allen & Overy rolled out Harvey to 3,500 lawyers after a 40,000-query trial
About 3,500 lawyers asked around 40,000 questions during the trial, followed by a firm-wide rollout across 43 offices.
New use cases, once a week
Short, sourced, no hype. Unsubscribe with one click.