{"asOf":"2026-10-03","doesNotChangeDepotPicks":true,"doesNotChangePriceSort":true,"doesNotChangeFreeIndex":true,"note":"Classification and failure modes are mechanisms. Case studies are included only when the source URL was fetched on 2026-10-03. A capability ceiling is not a company incident. Vendor figures are labeled as that vendor's report.","count":7,"catalogCount":27,"refused":["Replit agent database story (July 2025): The Register URL returned HTTP 403 and no first-party engineering postmortem was fetched. Not indexed.","CanLII HTML for 2024 BCCRT 149 returned a client-side block. The Civil Resolution Tribunal document was fetched instead and is the indexed source.","Cursor agent best-practices post loaded and is a product guide, not a postmortem. Not indexed as an incident. The University of Chicago study it mentions was not fetched.","Cognition 'Introducing Devin' (published 2024-03-12) duplicates the SWE-bench technical report. The report is indexed; the launch post is not a second study.","Anthropic many-shot jailbreaking research page loaded. It is an attack writeup, so it is not indexed and no procedure is stored.","OWASP LLM01:2025 was fetched and is cited on the prompt-injection failure mode only. Attack examples from that page are not copied into a case study.","Calder Lab and similar unsourced production-metric blogs were not fetched and are not indexed.","Google Research abstract for Data Cascades in High-Stakes AI loaded on 2026-10-03 (the abstract says 92% prevalence). Not indexed for data-etl: it is an interview study of ML data practice, not a pipeline job failure. The indexed data-etl study is the dbt Cloud status page."],"studies":[{"id":"swe-bench-2023","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","year":2023,"studyKind":"capability_ceiling","classIds":["coding","eval-judge"],"failureModeIds":["weak-verification","context-overflow"],"lesson":"The abstract describes 2,294 GitHub issues from 12 Python repositories. Resolving them often means coordinating edits across functions, classes, and files, and interacting with an execution environment. The abstract says Claude 2 solved 1.96% of the issues. Treat that figure as the paper's reported ceiling at publication, not a live Depot score.","sourceUrl":"https://arxiv.org/abs/2310.06770","asOf":"2026-10-03","notes":"Fetched the arXiv abstract (v3, last revised 11 Nov 2024). Not a company incident. Depot did not re-run the harness."},{"id":"swe-bench-verified-2024","title":"Introducing SWE-bench Verified","year":2024,"studyKind":"vendor_writeup","classIds":["coding","eval-judge"],"failureModeIds":["eval-contamination","benchmark-protocol-mismatch","weak-verification"],"lesson":"OpenAI's page says the original SWE-bench can grade a valid patch as wrong when unit tests are overly specific, the issue text is underspecified, or the environment fails to set up. They released a 500-sample human-validated subset, with difficulty slices of 196 tasks they mark as under 15 minutes and 45 they mark as over an hour. Cite the subset name with any score.","sourceUrl":"https://openai.com/index/introducing-swe-bench-verified/","asOf":"2026-10-03","notes":"Page date on the fetch: August 13, 2024. Model score tables on that page were not copied here."},{"id":"cognition-swe-bench-report-2024","title":"Cognition SWE-bench technical report","year":2024,"studyKind":"vendor_writeup","classIds":["coding","eval-judge"],"failureModeIds":["benchmark-protocol-mismatch"],"lesson":"Cognition's report says Devin resolved 13.86% of issues on a random 25% subset, unassisted, against a previous unassisted baseline of 1.96%, and that the best previous model resolved 4.80% when given the files to edit. The page itself distinguishes assisted from unassisted. Do not cite those percentages as the same protocol.","sourceUrl":"https://www.cognition.ai/blog/swe-bench-technical-report","asOf":"2026-10-03","notes":"Vendor self-report. article:published_time on the fetched page is 2024-03-15. Depot did not re-run the harness. The launch post Introducing Devin was not indexed separately."},{"id":"anthropic-building-effective-agents-2024","title":"Building effective agents","year":2024,"studyKind":"vendor_writeup","classIds":["orchestrator","coding","research"],"failureModeIds":["runaway-spend","instruction-drift"],"lesson":"The post separates workflows, where the path is orchestrated in code, from agents, where the model decides the path. It says agentic systems often trade latency and cost for task performance, and that the successful implementations they saw used simple composable patterns. A note on the fetched page says much of the tooling landscape described has changed since December 2024.","sourceUrl":"https://www.anthropic.com/engineering/building-effective-agents","asOf":"2026-10-03","notes":"Fetched page says Published Dec 19, 2024. This is a design note, not an incident with a measured outage."},{"id":"the-agent-company-2025","title":"TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks","year":2025,"studyKind":"capability_ceiling","classIds":["coding","browser","research","orchestrator"],"failureModeIds":["weak-verification"],"lesson":"The abstract describes a simulated software company where agents browse, write code, run programs, and communicate with coworkers. It says the most competitive agent they tested completed 30% of tasks autonomously. Read that as a ceiling inside their simulation, not as a measurement of any employer's production team.","sourceUrl":"https://arxiv.org/abs/2412.14161","asOf":"2026-10-03","notes":"Fetched arXiv v3, last revised 10 Sep 2025. Submitted 18 Dec 2024."},{"id":"agentbench-2024","title":"AgentBench: Evaluating LLMs as Agents","year":2024,"studyKind":"capability_ceiling","classIds":["coding","eval-judge"],"failureModeIds":["instruction-drift","hallucinated-tool-args","weak-verification"],"lesson":"The abstract says AgentBench uses 8 environments and that the main obstacles they identified were poor long-term reasoning, decision-making, and instruction following. A coding or tool agent that cannot stay on the instruction over many steps fails this kind of eval even if a single call looks fluent. The abstract's model count did not render as a number on the fetched page, so none is stored.","sourceUrl":"https://arxiv.org/abs/2308.03688","asOf":"2026-10-03","notes":"Fetched the arXiv abstract. Comment on the page: published in ICLR 2024."},{"id":"appworld-2024","title":"AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents","year":2024,"studyKind":"capability_ceiling","classIds":["coding","personal-assistant"],"failureModeIds":["collateral-side-effects","weak-verification"],"lesson":"The abstract describes 9 apps and 457 APIs, and 750 tasks whose checks allow more than one solution while also flagging unexpected changes. It says GPT-4o solved about 49% of normal tasks and about 30% of challenge tasks. A task that reaches the goal and also mutates something else is still a failed check in this design.","sourceUrl":"https://arxiv.org/abs/2407.18901","asOf":"2026-10-03","notes":"Fetched the arXiv abstract. Capability ceiling, not a company incident."}]}