Devin
An autonomous software engineer with its own IDE, shell and browser.
Group: Coding agents
Cognition documents Devin as an autonomous software engineer that writes, runs and tests code, available as Devin Cloud sessions with an IDE, shell and browser, plus Devin Desktop and a Devin CLI that can also steer cloud sessions from a terminal.
The decision in plain English
Keep the surfaces separate: Devin Cloud runs on Cognition-managed VMs, while the CLI runs on your own machine under configurable approval modes. Cognition says customer data may be used for model training by default, so a paid plan's Data Controls opt-out matters before connecting private repositories.
Best fit
Engineering teams delegating well-scoped, verifiable tickets who will review the draft PRs it returns.
Poor fit
Hard-to-verify projects with no completion criteria, or anyone needing a numeric published usage quota or default-off model training without a paid-plan opt-out.
Documented capabilities
Vendor statements, not verified task outcomes.
- Writes, runs and tests code in a cloud workspace Source · checked 2026-10-22
- Embedded IDE, shell and interactive browser, with takeover Source · checked 2026-10-22
- Devin CLI with tiered approval modes and optional OS sandbox Source · checked 2026-10-22
- Start, steer and resume Devin Cloud sessions from the terminal Source · checked 2026-10-22
- Admin security profiles restricting network, MCP, git and GitHub CLI access Source · checked 2026-10-22
Permissions and human control
- Documentation shows IDE takeover and an interactive browser for cloud sessions
- In the CLI's default Normal mode, read-only actions auto-approve while file writes and shell commands prompt; Smart mode auto-runs only actions a fast model judges safe and never auto-approves installs, rm, sudo, mutating git or access to dotenv and key material; Bypass auto-approves everything; Autonomous mode pairs with an OS sandbox where shell and fetches auto-approve but edit/write tools still prompt
- Organisation-level deny and ask rules override every user permission mode
- Admin security profiles can allowlist network destinations and MCP servers, set git read-only or full access, remove the GitHub CLI token and make Devin's own management tools read-only; sessions without a profile run unrestricted
- Secrets can be scoped to the organisation, a person, a repository or one session, are encrypted at rest and are bound only to the commands that need them
Documented controls do not prove that an agent always follows them.
Limits and open questions
- Teams pricing conflicts: pricing page says $80/month plus $40 per full seat; billing docs say an $80 minimum met by seats and credits. Confirm the offered total before payment.
- Vendor explicitly says documentation may be out of date
- Quotas are described as daily and weekly allowances but not published as numbers
- Model training is on by default; only paid plans can opt out, and on Teams only an administrator can
- Security profiles are admin-configured: without one, sessions run unrestricted, and on customer-run Outposts the network policy must be enforced by the operator's own infrastructure
- Smart approval mode is rolling out gradually and may not be available
Privacy and security
Re-verified 22 October 2026 against Cognition's Platform Terms of Service (updated 30 June 2026) and privacy policy (updated 9 March 2026). Customer Data may be used for model training and service improvement by DEFAULT (ToS 3.3.1). Paid tiers can opt out; after opt-out, Customer Data is not used for training and zero data retention is enabled with Cognition's model providers. For the Teams tier only an administrator may opt out; Enterprise customer data is never used for training without express prior written consent (per Cognition's security page). ZDR does not preclude retention of data flagged by automated safety/abuse classifiers, safety/AUP review, or legal process (ToS 3.3.3). The privacy policy adds: voice-input audio is deleted after transcription unless stated otherwise, and deletion of personal information can be requested. Use restrictions prohibit building competing products or training competing models. Vendor documents, not independently audited.
Feature-by-feature: what is documented and what is not
Official sources checked 11 October 2026. A documented feature is a vendor statement, not proof of success.
| Feature | Evidence status | Detail and limit |
|---|---|---|
| Cloud versus local | Separate controls | Cloud uses managed VMs. Local CLI permissions must not be treated as proof of Cloud behaviour. Source |
| CLI Normal and Accept Edits | Documented | Normal auto-approves reads, prompts for writes/shell. Accept Edits auto-approves workspace edits, but shell/outside writes still prompt. Source |
| Smart and Bypass | Different risk | Smart judges routine actions and prompts on uncertainty; sensitive categories never auto-approve. Bypass auto-approves all tool calls; organisation deny/ask rules still apply. Source |
| Autonomous sandbox | Not universal write permission | Sandbox allows shell/fetch automatically within OS limits. Direct edit/write tools still prompt and granted write scope can expand the sandbox. Source |
| Cloud security profiles | Must be configured | Profiles can restrict network, MCP, git and GitHub CLI access. No-profile sessions run unrestricted; customer Outpost network controls depend on operator infrastructure. Source |
| Training and retention | Plan-dependent vendor claim | Training may be on by default. Paid users can opt out; Teams requires an admin. Enterprise training needs express written consent. Opt-out enables provider zero-retention, not deletion of Cognition-held records. Source |
| Teams pricing | Official source conflict | Pricing page says $80 base plus $40/full seat; billing docs describe an $80 minimum met by seats/credits. Both cap self-serve Teams at 200. Confirm the actual offer. Source |
| Quotas and credits | Numeric quotas unknown | Pro/full seats have daily/weekly allowance; Max weekly only. Teams automations/review use shared credits, not seat quota. Numeric allowances are not published here. Source |
How to start with Devin narrowly
- Choose Cloud or local CLI first, then one small ticket with tests and a reviewable diff.
- Before private repository access, review training opt-out and organisation permission rules.
- Use Normal mode for local review or an explicitly configured Cloud security profile; do not select Bypass as a safety default.
- Confirm quota, shared credits and the actual Teams quote before paid work.
Official product/setup source. These are documentation-based steps, not a hands-on setup test.
Common questions about Devin
What is Devin for?
Engineering teams delegating well-scoped, verifiable tickets who will review the draft PRs it returns. The vendor describes it as: Cognition documents Devin as an autonomous software engineer that writes, runs and tests code, available as Devin Cloud sessions with an IDE, shell and browser, plus Devin Desktop and a Devin CLI that can also steer cloud sessions from a terminal.
Who should look elsewhere?
Hard-to-verify projects with no completion criteria, or anyone needing a numeric published usage quota or default-off model training without a paid-plan opt-out.
How much does Devin cost?
Devin's pricing page (re-verified 2 November 2026) lists Free at $0 with a light quota, limited models, unlimited inline edits and Tab completions; Pro at $20/month adding full model availability, Devin Cloud access, and free use of SWE-2 (Cognition's latest model; the page now shows this without the previously advertised 16 October 2026 end date); Max at $200/month with significantly higher quotas; Teams at $80/month minimum plus $40/month per full seat; extra usage at API pricing. Plan structure confirmed against the self-serve billing doc (2 November 2026). The ChatGPT-subscription payment option claim was last verified 11 October 2026 and was not re-confirmed today.
What can it access and what needs my approval?
Documentation shows IDE takeover and an interactive browser for cloud sessions In the CLI's default Normal mode, read-only actions auto-approve while file writes and shell commands prompt; Smart mode auto-runs only actions a fast model judges safe and never auto-approves installs, rm, sudo, mutating git or access to dotenv and key material; Bypass auto-approves everything; Autonomous mode pairs with an OS sandbox where shell and fetches auto-approve but edit/write tools still prompt Organisation-level deny and ask rules override every user permission mode Admin security profiles can allowlist network destinations and MCP servers, set git read-only or full access, remove the GitHub CLI token and make Devin's own management tools read-only; sessions without a profile run unrestricted Secrets can be scoped to the organisation, a person, a repository or one session, are encrypted at rest and are bound only to the commands that need them
What happens to my data?
Re-verified 22 October 2026 against Cognition's Platform Terms of Service (updated 30 June 2026) and privacy policy (updated 9 March 2026). Customer Data may be used for model training and service improvement by DEFAULT (ToS 3.3.1). Paid tiers can opt out; after opt-out, Customer Data is not used for training and zero data retention is enabled with Cognition's model providers. For the Teams tier only an administrator may opt out; Enterprise customer data is never used for training without express prior written consent (per Cognition's security page). ZDR does not preclude retention of data flagged by automated safety/abuse classifiers, safety/AUP review, or legal process (ToS 3.3.3). The privacy policy adds: voice-input audio is deleted after transcription unless stated otherwise, and deletion of personal information can be requested. Use restrictions prohibit building competing products or training competing models. Vendor documents, not independently audited.
Has AgentComparison tested it?
No. This record is built from the vendor's own documentation, checked 2026-10-11. Vendor claims are attributed, not confirmed.
How to evaluate Devin yourself
- Pick one low-risk task that matches its documented capabilities: writes, runs and tests code in a cloud workspace.
- Write the expected output and what counts as failure before you start.
- Connect the minimum access needed, and check approval settings first.
- Run it twice and compare, then review every action it took.
- Check cost after any free allowance. Unknown price is not free.
Related
Documented use cases: Software development and repository work.
- Claude Code (product): Developers delegating repository changes from a terminal.
- Replit Agent (product): Building apps and related artifacts from natural-language requests.
- Cursor cloud agents (product): Developers who want background work on repository branches and can review diffs, tests and artifacts before a human merges the draft pull request. Configure restricted egress and minimum repository access first.
- Jules (product): GitHub developers with a working project setup who want bounded bug fixes, dependency maintenance, documentation or tests returned for review while they work on something else.
- Claude Code vs Devin
- Devin pricing explained
- AI agent use cases by job
- Privacy and approval checklist
- Compare two agents side by side
- Latest agent updates
Sources and history
- https://devin.ai/pricing · official · read 11 October 2026
- https://docs.devin.ai/get-started/devin-intro · official · read 11 October 2026
- https://docs.devin.ai/admin/billing/self-serve · official · read 11 October 2026
- https://docs.devin.ai/cli/reference/permissions · official · read 11 October 2026
- https://docs.devin.ai/cli/cloud · official · read 11 October 2026
- https://docs.devin.ai/product-guides/security-profiles · official · read 11 October 2026
- https://docs.devin.ai/admin/security · official · read 11 October 2026
- https://cognition.com/legal/privacy-policy · official · read 11 October 2026
- https://cognition.com/legal/platform-terms-of-service · official · read 11 October 2026
Change history
- 2026-11-02: undefined
- 2026-10-11: Expanded product-specific feature evidence and narrow setup from fresh official docs. Costs, credential exposure and limits remain explicit. Documentation research, not tested.
- 2026-10-10: Flagged conflicting official Teams billing models and corrected pricing guide membership cap to 200. Pricing sources reread; no other product fields reverified.
- 2026-10-08: Refreshed from the pricing page and seven official docs: added the default-on model-training opt-out and zero-data-retention claim, retention scope, SOC 2 Type II statement, admin security profiles, CLI approval modes and secrets scoping. Pricing synced with devin.ai/pricing. Documentation research only; not tested.
- 2026-10-01: Initial documentation research. No hands-on testing.
- 2026-09-29: Cognition blog: GPT-6.1 Sol available in Devin Desktop and Devin CLI. Benchmark figures in the post are Cognition's own.
- 2026-10-22: Field-level audit: training-default-on + paid opt-out + ZDR claims re-verified against the current Platform ToS (30 June 2026) including the safety/abuse and legal-process exceptions to ZDR; privacy policy (9 March 2026) adds voice-audio deletion after transcription; legal URLs corrected to cognition.com (devin.ai/terms and /privacy 404).
- 2026-11-02: Pricing re-verified against devin.ai/pricing and the self-serve billing doc: plan prices unchanged; SWE-2 free use in Pro no longer carries the 16 October 2026 end date on the page. Documentation research only.
Documentation overview expanded with current pricing/access sources. No hands-on results claimed.
Report a correction