{"id":"cognition-devin-v2-spec-mode--cognition-ai","name":"Cognition Devin v2 / Spec Mode","url":"https://cognition.com/","page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/cognition-devin-v2-spec-mode--cognition-ai","family":"agents","section":"Agent IDEs & coding harnesses","sections":["Agent IDEs & coding harnesses"],"tier":1,"last_verified_at":"2026-10-29","lifecycle":{"status":"active","severity":0,"note":null},"taxonomy":null,"cells":{"type":{"value":"Devin successor — autonomous coding agent + spec-mode (cross-listing)","citation":"https://cognition.ai","status":"real-data","tier":"T2","source_class":"vendor"},"desc":{"value":"Cross-listing of Cognition's Devin product framed at the harness level rather than the memory layer. Devin 2.0 (Mar 2025) added cheaper concurrent sessions; Spec Mode (Aug 2025, post-Windsurf-IP acquisition) integrates Windsurf-style spec authoring. The Coding-agent-memory row remains canonical for the memory framing.","citation":"https://cognition.ai","status":"real-data","tier":"T2","source_class":"vendor"},"claims":{"value":"Devin 2.0 Mar 2025; Spec Mode Aug 2025; $400M raise at $10.2B val Sep 2025; absorbed remaining Windsurf IP Aug 2025.","citation":"https://cognition.ai","status":"real-data","tier":"T2","source_class":"vendor"},"modalities":{"value":"text","citation":"https://cognition.ai","status":"real-data","tier":"T2","source_class":"vendor"},"created":{"value":"2024-03","citation":"https://cognition.ai","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"latest-release":{"value":"Devin release notes update (2026-10-26)","citation":"https://docs.devin.ai/release-notes/overview","status":"real-data","tier":"T2","last_verified_at":"2026-10-27","source_class":"vendor"},"license":{"value":"not applicable — not OSS","citation":null,"status":"not-applicable","tier":"T3"},"gh":{"value":"not applicable — no GitHub repo","citation":null,"status":"not-applicable","tier":"T3","last_verified_at":"2026-05-14"},"mindshare":{"value":"50+ HN threads on Devin since launch; benchmark of SWE-bench-Verified hype-cycle","citation":"https://cognition.ai","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"citations":{"value":"not applicable — not academic","citation":null,"status":"not-applicable","tier":"T3","last_verified_at":"2026-05-13"},"funding":{"value":"Over $2B Series E at $48B valuation (2026-09-08), led by Andreessen Horowitz and Accel with Founders Fund, General Catalyst and others","citation":"https://cognition.com/blog/series-e","status":"real-data","tier":"T2","last_verified_at":"2026-10-27","source_class":"vendor"},"customers":{"value":"$150M+ ARR (reported); Goldman Sachs, Citi, Dell, Cisco, Ramp, MongoDB","citation":"https://cognition.ai","status":"real-data","tier":"T2","source_class":"vendor"},"pricing":{"value":"Free $0; Pro $20/mo; Max $200/mo; Teams $80/mo plus $40/mo per full seat; Enterprise custom","citation":"https://devin.ai/pricing","status":"real-data","tier":"T2","source_class":"vendor"},"compliance":{"value":"SOC 2 Type II","citation":"https://cognition.ai","status":"real-data","tier":"T2","source_class":"vendor"},"data-handling":{"value":"Enterprise: never trains; opt-out","citation":"https://cognition.ai","status":"real-data","tier":"T2","source_class":"vendor"},"deployment":{"value":"Managed-only — Cognition cloud agents plus Devin Desktop and CLI; enterprise plan offers a dedicated deployment option","citation":"https://devin.ai/pricing","status":"real-data","tier":"T2","source_class":"vendor"},"hq":{"value":"US (San Francisco; Cognition)","citation":"https://cognition.ai","status":"real-data","tier":"T2","source_class":"vendor"},"founders":{"value":"Scott Wu, Steven Hao, Walden Yan — Cognition founders","citation":"https://cognition.ai","status":"real-data","tier":"T2","source_class":"vendor"},"volume":{"value":"searched not found","citation":"https://cognition.ai","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"perf":{"value":"searched not found","citation":"https://cognition.ai","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"repro":{"value":"not applicable — not a research paper","citation":null,"status":"not-applicable","tier":"T3"},"code-release":{"value":"not applicable — not a research paper","citation":null,"status":"not-applicable","tier":"T3"},"api-surface":{"value":"Web app, Devin Desktop, Devin CLI, Slack and REST API","citation":"https://docs.devin.ai/release-notes/overview","status":"real-data","tier":"T2","source_class":"vendor"},"latency":{"value":"searched not found","citation":"https://cognition.ai","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"throughput":{"value":"searched not found","citation":"https://cognition.ai","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"backend-storage":{"value":"cloud session state + Knowledge","citation":"https://cognition.ai","status":"real-data","tier":"T2","source_class":"vendor"},"multi-tenancy":{"value":"per-tenant","citation":"https://cognition.ai","status":"real-data","tier":"T2","source_class":"vendor"},"encryption":{"value":"TLS + AES-256","citation":"https://cognition.ai","status":"real-data","tier":"T2","source_class":"vendor"},"sso-rbac":{"value":"SSO + RBAC","citation":"https://cognition.ai","status":"real-data","tier":"T2","source_class":"vendor"},"embedding-model":{"value":"not applicable — not a memory product","citation":null,"status":"not-applicable","tier":"T3"},"consistency":{"value":"searched not found","citation":"https://cognition.ai","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"versioning":{"value":"searched not found","citation":"https://cognition.ai","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"tombstoning":{"value":"searched not found","citation":"https://cognition.ai","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"schema-evolution":{"value":"searched not found","citation":"https://cognition.ai","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"namespace":{"value":"per-Knowledge + per-org","citation":"https://cognition.ai","status":"real-data","tier":"T2","source_class":"vendor"},"contradiction":{"value":"LLM resolves","citation":"https://cognition.ai","status":"real-data","tier":"T2","source_class":"vendor"},"forgetting":{"value":"searched not found","citation":"https://cognition.ai","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"mcp-support":{"value":"yes — MCP marketplace plus custom MCP servers (STDIO and remote) configurable in Devin; Devin also ships its own Devin MCP server","citation":"https://docs.devin.ai/work-with-devin/mcp","status":"real-data","tier":"T2","source_class":"vendor"},"a2a-support":{"value":"searched not found","citation":"https://cognition.ai","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"otel":{"value":"searched not found","citation":"https://cognition.ai","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"webhooks":{"value":"Slack + GitHub webhooks","citation":"https://cognition.ai","status":"real-data","tier":"T2","source_class":"vendor"},"import-export":{"value":"searched not found","citation":"https://cognition.ai","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"integration-count":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"orchestration":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"programmatic-control":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"vendor-benchmarks":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3","last_verified_at":"2026-05-13"},"pricing-specifics":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"agent-abstraction":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"memory-primitives":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"llm-lock":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"runtimes":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"session-handling":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"validated-verticals":{"value":"coding agents — enterprise (financial services overweight)","citation":"https://cognition.ai","status":"real-data","tier":"T2","source_class":"vendor"},"time-to-running":{"value":"<10min (Devin sign-up)","citation":"https://cognition.ai","status":"real-data","tier":"T2","source_class":"vendor"},"anti-fit":{"value":"expensive per-session; not for non-coding","citation":"https://cognition.ai","status":"real-data","tier":"T2","source_class":"vendor"},"optimised-for":{"value":"fully autonomous SWE work + Spec Mode + Knowledge","citation":"https://cognition.ai","status":"real-data","tier":"T2","source_class":"vendor"},"adjacent-infrastructure":{"value":"absorbed Windsurf IP (Aug 2025); Anthropic + OpenAI models","citation":"https://cognition.ai","status":"real-data","tier":"T2","source_class":"vendor"},"pros":{"value":"Highest valuation in the category ($10.2B); only agent product to consolidate via M&A (Windsurf IP); enterprise customer logos are richest in category.","citation":"https://cognition.ai","status":"real-data","tier":"T2","source_class":"vendor"},"cons":{"value":"Cost per autonomous session is high; opaque pricing relative to seat-based competitors; M&A history creates roadmap risk.","citation":"https://cognition.ai","status":"real-data","tier":"T2","source_class":"vendor"},"links":{"value":"cognition.ai; devin.ai; Sep 2025 Series E coverage","citation":"https://cognition.ai","status":"real-data","tier":"T2","source_class":"vendor"},"obs-langsmith":{"value":"no","citation":"https://cognition.ai/","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"obs-opentelemetry":{"value":"no","citation":"https://cognition.ai/","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"obs-datadog":{"value":"no","citation":"https://cognition.ai/","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"obs-helicone":{"value":"no","citation":"https://cognition.ai/","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"obs-weave":{"value":"no","citation":"https://cognition.ai/","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"obs-langfuse":{"value":"no","citation":"https://cognition.ai/","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"obs-arize":{"value":"no","citation":"https://cognition.ai/","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"obs-custom":{"value":"Closed product; no third-party observability surface","citation":"https://cognition.ai/","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"cost-token-budget":{"value":"no","citation":"https://docs.devin.ai/","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"cost-prompt-caching":{"value":"no","citation":"https://docs.devin.ai/","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"cost-semantic-caching":{"value":"no","citation":"https://docs.devin.ai/","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"cost-batching":{"value":"no","citation":"https://docs.devin.ai/","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"cost-model-routing":{"value":"no","citation":"https://docs.devin.ai/","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"cost-streaming-only":{"value":"no","citation":"https://docs.devin.ai/","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"cost-observability-cost-attribution":{"value":"yes","citation":"https://docs.devin.ai/onboard-devin/usage-based-pricing","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"eval-langsmith-evals":{"value":"no","citation":"https://www.cognition.ai/","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"eval-braintrust":{"value":"no","citation":"https://www.cognition.ai/","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"eval-weights-and-biases-agent":{"value":"no","citation":"https://www.cognition.ai/","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"eval-helicone-evals":{"value":"no","citation":"https://www.cognition.ai/","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"eval-custom-test-harness":{"value":"yes","citation":"https://www.cognition.ai/blog/devin-2","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"eval-human-loop":{"value":"yes","citation":"https://www.cognition.ai/blog/devin-2","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"eval-production-traffic-replay":{"value":"no","citation":"https://www.cognition.ai/","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"commit-trajectory":{"value":"not applicable — no GitHub repo","citation":null,"status":"not-applicable","tier":"T3","last_verified_at":"2026-05-14"},"citation-trajectory":{"value":"not applicable — non-paper row","citation":null,"status":"not-applicable","tier":"T3","last_verified_at":"2026-05-14"},"download-trajectory":{"value":"not applicable — not published as a package","citation":null,"status":"not-applicable","tier":"T3","last_verified_at":"2026-05-14"},"cost-input-usd-per-mtok":{"value":"0","citation":"https://cognition.ai","status":"real-data","tier":"T2","source_class":"vendor"},"cost-output-usd-per-mtok":{"value":"0","citation":"https://cognition.ai","status":"real-data","tier":"T2","source_class":"vendor"},"cost-tier":{"value":"free","citation":"https://cognition.ai","status":"real-data","tier":"T2","source_class":"vendor"},"cost-pricing-model":{"value":"free-tier","citation":"https://cognition.ai","status":"real-data","tier":"T2","source_class":"vendor"},"cost-last-verified":{"value":"2026-06-29","citation":"https://cognition.ai","status":"real-data","tier":"T2","source_class":"vendor"},"capability-composite-score":{"value":"76","citation":null,"status":"estimate","tier":"T3"},"capability-band":{"value":"frontier","citation":null,"status":"estimate","tier":"T3"},"capability-benchmark-sources":{"value":"SWE-bench Lite 13.86% (original Devin, Mar 2024), Devin 2.0 / Spec Mode reported SWE-bench Verified mid-50s with frontier models (2025)","citation":null,"status":"estimate","tier":"T3"},"capability-last-verified":{"value":"2026-06-29","citation":null,"status":"estimate","tier":"T3"},"use-case-tags":{"value":"code-generation-focused, long-running-session, scoped-agentic","citation":null,"status":"estimate","tier":"T3"},"use-case-anti-tags":{"value":"offline-capable, latency-sensitive","citation":null,"status":"estimate","tier":"T3"},"adoption-accelerator":{"value":"","citation":null,"status":"no-data","tier":"T3"},"architecture-deployment-locus":{"value":"hybrid","citation":"https://devin.ai/","status":"real-data","tier":"T2","source_class":"vendor"},"licensing-bucket":{"value":"commercial","citation":"https://devin.ai/pricing","status":"real-data","tier":"T2","source_class":"vendor"},"positioning-platform-vs-product":{"value":"product","citation":"https://docs.devin.ai/","status":"real-data","tier":"T2","source_class":"vendor"},"taxonomy-three-layer-rollup":{"value":"agent-infra","citation":"https://github.com/MrPeppersDev/agent-infrastructure-landscape/blob/main/docs/schema/section-to-three-layer-rollup.json","status":"real-data","tier":"T1","source_class":"repo"},"developer-activity-opendigger":{"value":"","citation":null,"status":"no-data","tier":"T3"},"freshness-date":{"value":"2026-10-29","citation":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/cognition-devin-v2-spec-mode--cognition-ai","status":"real-data","tier":"T2","source_class":"catalog"},"compliance-certifications":{"value":"","citation":null,"status":"no-data","tier":"T3"},"sdk-languages":{"value":"","citation":null,"status":"no-data","tier":"T3"},"protocol-support":{"value":"","citation":null,"status":"no-data","tier":"T3"},"maturity":{"value":"","citation":null,"status":"no-data","tier":"T3"}},"corroboration":{"cited_cells":63,"third_party_cells":0},"edges":{"outgoing":[{"source":"cognition-devin-v2-spec-mode--cognition-ai","target":"anthropic-claude-foundation-models--anthropic-com","type":"runtime-dependency","evidence":"adjacent-infrastructure cell: absorbed Windsurf IP (Aug 2025); Anthropic + OpenAI models","citation":"https://cognition.ai"},{"source":"cognition-devin-v2-spec-mode--cognition-ai","target":"openai-gpt-family-gpt-5-gpt-4o-o3-o4--openai-com","type":"runtime-dependency","evidence":"adjacent-infrastructure cell: absorbed Windsurf IP (Aug 2025); Anthropic + OpenAI models","citation":"https://cognition.ai"}],"incoming":[]},"history":[{"date":"2026-10-29","commit":"a5ff184341","pr":305,"kind":"update","changes":[{"field":"url","label":"Homepage","from":"https://cognition.ai","to":"https://cognition.com/"}]},{"date":"2026-10-27","commit":"cba4aa2502","pr":273,"kind":"update","changes":[{"field":"latest-release","label":"Latest release","from":"not applicable — not OSS","to":"Devin release notes update (2026-10-26)","source":"https://docs.devin.ai/release-notes/overview"},{"field":"pricing","label":"Pricing","from":"Free + paid; Spec Mode in Pro","to":"Free $0; Pro $20/mo; Max $200/mo; Teams $80/mo plus $40/mo per full seat; Enterprise custom","source":"https://devin.ai/pricing"},{"field":"funding","label":"Funding / ownership","from":"$1.1B total $10.2B val Series E 2025-09","to":"Over $2B Series E at $48B valuation (2026-09-08), led by Andreessen Horowitz and Accel with Founders Fund, General Catalyst and others","source":"https://cognition.com/blog/series-e"},{"field":"deployment","label":"Deployment","from":"Cloud","to":"Managed-only — Cognition cloud agents plus Devin Desktop and CLI; enterprise plan offers a dedicated deployment option","source":"https://devin.ai/pricing"},{"field":"mcp-support","label":"MCP support","from":"native (Devin MCP integrations)","to":"yes — MCP marketplace plus custom MCP servers (STDIO and remote) configurable in Devin; Devin also ships its own Devin MCP server","source":"https://docs.devin.ai/work-with-devin/mcp"}]}],"license":"CC-BY-4.0","source":"https://github.com/MrPeppersDev/agent-infrastructure-landscape/blob/main/data/landscape.json"}