---
title: "Jiro vs Devin (2026): Model Billing, Harness Choice and Team Fit"
canonical: https://jiro.bot/compare/devin
last_updated: 2026-11-06
---

# Jiro vs Devin (2026): Model Billing, Harness Choice and Team Fit

Updated 2026-11-06

> **Jiro vs Devin: which background coding agent should I use?**
>
> Pick Jiro if your team of five to twenty engineers already holds Claude or ChatGPT subscriptions: it runs Claude Code, Codex or Cursor Agent against those credentials, charges a flat runtime fee of $99 or $250 a month, and marks up no tokens. Jiro is a background coding agent by Nori. Pick Devin if you want one vendor supplying the agent, the model routing and the usage bill, or if Microsoft Teams, GitLab, Linear-triggered sessions or a dedicated single-tenant Devbox are requirements. It is not Amazon's Kiro or Atlassian's Jira.

## Jiro vs Devin, row by row

|  | Jiro | Devin |
|---|---|---|
| Product | Background coding agent by Nori | Autonomous software engineer (Cognition) [1] |
| Agent that runs | Claude Code, Codex, Cursor, OpenCode, pi-acp [2] | Devin's own agent; Desktop also hosts ACP agents [3] |
| Model and credentials | Your Claude/ChatGPT login or API key; Cursor key [4] | Anthropic, OpenAI, Google, Cognition SWE; Adaptive routing [5] |
| Token pricing | Your keys, zero token markup [6] | Adaptive: $0.50 in / $2.00 out per million tokens [7] |
| Own subscription | Claude or ChatGPT login accepted for Claude Code and Codex [4] | Link a personal ChatGPT plan for GPT usage only [8] |
| Execution environment | Isolated cloud environment with your repos and tools [9] | Blueprint builds a snapshot; every session boots from it [10] |
| Environment setup | Org setup script prepares each environment [11] | Blueprint builds a snapshot [10] |
| Where work starts | Slack, web, Discord, terminal, schedules, webhooks [12] | GitHub/GitLab/Bitbucket/ADO; Slack, Teams, Linear, Jira [13] |
| Scheduled and event work | Cron, one-off reminders, webhooks [14] | Schedules, webhooks, Slack/Git/Linear/Jira/PagerDuty events [15] |
| Output | PRs, commits, comments for review [16] | Opens PRs and answers PR comments [17] |
| PR upkeep | Returned for your review [16] | Stacked PRs with self-resolved conflicts; GitHub.com only [18] |
| Reusable instructions | One skillset, translated per agent [19] | SKILL.md files (Agent Skills standard) in repos or Customize page [20] |
| Tenancy | Single-tenant per organization [21] | Cognition-hosted single-tenant VPC via PrivateLink or IPSec [22] |
| Your own infrastructure | Nori cloud, or a dedicated deployment in your AWS account [23] | Outposts: sessions on your machines; brain stays in Devin cloud [24] |
| Audit | Every session and action logged [25] | Not covered by the sources cited here |

Rows show each vendor's own published wording, dated in the sources list. Where a source did not cover a row, the cell says so.

## Plans and prices (checked 2026-11-06)

| Plan | Monthly price | Included | Overage |
|---|---|---|---|
| Jiro trial | Free for 30 days, no card [26] | Five runtimes [27] | None |
| Jiro Developer | $99 [26] | One user, up to three persistent runtimes | None; tokens stay on your own plan or key [6] |
| Jiro Team | $250 [26] | Multiple users sharing five runtimes | None; zero token markup [6] |
| Devin Free | Free [28] | Limited usage, Devin Review, DeepWiki [29] | On-demand credits |
| Devin Pro | $20 [28] | Daily and weekly quota; up to 10 concurrent sessions [30] | On-demand credits that never expire [29] |
| Devin Max | $200 [28] | Larger weekly quota, no daily cap; no concurrency cap | On-demand credits that never expire |
| Devin Teams | $40 per full seat with an $80 minimum [28] | Up to 200 members; $40 full seats; free flex seats; $80 minimum [31] | Shared credit pool; Adaptive at $0.50 in / $2.00 out per million tokens [7] |
| Devin Enterprise | Custom [32] | ACU contract; dedicated deployment option [22] | ACUs |

## What is the difference between Jiro and Devin?

Devin is a vertically integrated agent: Cognition builds the agent loop, routes the model, hosts the machine and sells the tokens. [3] [5] Jiro is a managed place to run agents you already use. It hosts one of five harnesses, Claude Code and Codex chief among them, inside its own isolated cloud environment with your repositories already cloned, and hands back a pull request. [2] [9] [16]

That single design choice explains most rows in the table. Devin can route every step to a different model because it owns the loop. Jiro cannot, and does not try. Devin resells tokens because the loop is its product. Jiro passes your own credential through and bills only for runtimes. [4] [6] Devin runs in Cognition's cloud or on your desktop; Jiro runs in Nori's cloud or, as a dedicated deployment, inside the customer's own AWS account. [33] [23] Everything else is detail.

## How does Jiro bill compared with Devin?

Jiro charges for runtimes and nothing else: Developer is $99 monthly for one person, Team is $250 monthly for a group sharing five, and the trial is free for 30 days. [26] Tokens never appear on Nori's invoice because the harness signs in with your Claude or ChatGPT account or your own API key. [6] [4] A Claude subscriber runs `claude setup-token` once on their laptop, gets a year-long token for their plan tier, and connects it. [34]

Devin bundles the model. Pro is $20 a month and Max is $200, each with a usage quota; Teams is $40 per full seat per month, subject to an $80 monthly minimum. [28] Past the quota you buy on-demand credits, and when Adaptive is routing, those credits drain at $0.50 in and $2.00 out for every million tokens, regardless of which model it chose. [29] [7] A user on Pro, Max or Teams may link a personal ChatGPT plan, but only GPT requests move onto it; Claude and Gemini usage and the machine time still consume Devin quota. [8]

So the comparison hinges on one fact about your company. If it already pays Anthropic or OpenAI, Jiro's model cost is sunk and Devin's is additive. If it pays neither, Devin's bundle may be the simpler purchase.

## Which agents and models does each one run?

Devin runs Cognition's own agent in the cloud, with models from Anthropic, OpenAI, Google and Cognition's SWE family behind an Adaptive router that picks one per task. [3] [5] Enterprise accounts have Adaptive off until an admin enables it. [7] Devin Desktop, Windsurf's successor, runs ACP agents from other vendors alongside Devin. [35] [3]

Jiro runs no model and no agent of its own. Its first-class harnesses are Claude Code and Codex, which accept a subscription login or API key, plus Cursor Agent (Cursor key) and the OpenCode and pi-acp agents on any compatible endpoint. [2] [4] Gemini was removed from managed sessions. [36] A team that has spent a year tuning CLAUDE.md files keeps all of it, because a Nori skillset is authored once and emitted as a CLAUDE.md for Claude Code or an AGENTS.md for Codex and most others. [19] Changing harness is a setting, not a vendor change.

## Where does the work run, and who prepares the environment?

Both give the agent a real machine rather than a sandboxed shell. Devin's environment is a Linux virtual machine described by a blueprint and frozen as a snapshot; every session boots a fresh copy, and nothing the session changes persists back. [10] Devin can propose that blueprint by inspecting your repository. Jiro's equivalent is an organisation setup script that installs dependencies and prepares each session's isolated cloud environment, repositories and tooling included. [11] [9] A claimed machine belongs to one session at a time. [37]

Secrets differ in shape. Devin's Secrets feature spans four scopes (organisation, personal, repository, session) and three kinds (raw keys, browser cookies, TOTP), handing each value only to the step that uses it. [38] Jiro's credentials are the model login or key, the GitHub App or token, and whatever the MCP catalog and integrations need. [39] [40] Devin's secrets model is richer; Jiro's is simpler to audit.

## Where can the team start work: Slack, tickets, schedules?

Slack works on both. Mention @Devin in a channel and it replies in the thread, with optional two-way sync and a dedicated code channel per session. [41] Mention Jiro's bot and it replies in a thread too, and every later reply there continues the same session. [42]

Beyond Slack, Devin goes wider. It also listens in Microsoft Teams, Linear, Jira, PagerDuty and Pylon, and its Automations fire on events from those tools, from GitHub and GitLab, from schedules and from webhooks. [13] [15] Jiro's documented ways in are the web dashboard, Slack or Discord, the Handroll terminal, and cron schedules, one-off reminders or webhooks. [12] [14] Linear and Jira are among Jiro's integrations, so the agent can read and update tickets, but a ticket event does not start a session. [43] Teams that want a session per new ticket should weigh that carefully.

## What comes back: pull requests and their upkeep

Jiro's deliverable is something a person reviews: a PR most often, sometimes a commit or a comment, and you merge it or send it back. [16] Devin opens pull requests and keeps answering comments on them until the session is archived. [17] It can also split a large change into a stack of PRs that land bottom-up, resolve conflicts between the layers itself and fix CI across the stack, though only on GitHub.com repositories. [18]

On PR mechanics Devin is ahead. Jiro's answer is about what goes into the PR rather than how many there are: at Miravoice, Jiro's share of merged PRs has passed 25%, and the CTO reckons it saves him five hours weekly. [44]

## How do deployment and tenancy compare?

Nori gives each hosted organisation a single-tenant broker under its own subdomain, and keeps a searchable log of everything each session did. [21] [25] For customers who need the machines inside their own perimeter, a dedicated BYOC deployment runs private EC2 session machines in customer-controlled AWS infrastructure. [23]

Devin's Enterprise option, the Customer Dedicated Deployment, puts the Devbox in a customer-isolated single-tenant VPC run by Cognition, which your network reaches over AWS PrivateLink or an IPSec tunnel. [22] The brain, Devin's planning and inference service, always resides in Cognition's cloud, in every deployment model. [45] Outposts, available on the self-serve plans, lets your own machines execute sessions while the brain stays remote. [24] The two shapes differ: Jiro's BYOC deployment puts the session machines, where the agent itself runs, inside your own AWS account, while Devin keeps its planning service in Cognition's cloud by design. Ask your security team which of those they have already approved.

## What would a team of eight pay?

On Jiro, eight engineers fit on Team at $250 a month, sharing five runtimes, and their tokens come from the Claude or ChatGPT seats the company already buys. [26] [6] If those seats do not exist yet, budget for them: Claude Max is $100 a month per person, and Anthropic's own figure for heavy Claude Code use is $150 to $250 a developer each month on the API. [46] [47]

On Devin, eight full seats at $40 each clear the $80 monthly minimum easily, so the seat line is predictable. [31] The credits line is not. It scales with how hard the team leans on the agent, at $0.50 in and $2.00 out per million tokens under Adaptive. [7] Flex seats cost nothing but draw on that same pool. [31]

Concurrency is the other number to check. Devin Teams has no concurrency cap; Free and Pro stop at ten sessions. [30] Jiro's ceiling is the runtime count, five on Team, and runtimes sleep when idle. [27] A team that fans out a dozen tasks at once will hit Jiro's limit. Most teams of eight will not.

## When Devin is the better choice

Choose Devin when reach matters more than model economics. It is the only one of the two that listens in Microsoft Teams, starts sessions from Linear, Jira, PagerDuty or Pylon events, and works with GitLab, Bitbucket and Azure DevOps as well as GitHub. [13] [15]

Choose it when you want the model decision made for you. Adaptive routes each step across Anthropic, OpenAI, Google and Cognition's own models, and on self-serve plans the price per token is the same whichever it picks. [5] [7]

Choose it if the IDE is part of the deal. Devin Desktop grew out of Windsurf and hosts third-party ACP agents beside Devin. [35] [3]

Choose it for PR mechanics: stacked pull requests with self-resolved conflicts, and an agent that answers reviewer comments for as long as the session stays open. [18] [17]

And choose it if your enterprise wants a single-tenant Devbox that Cognition hosts behind PrivateLink and accepts that planning stays in Cognition's cloud. [22] That is a well-understood shape for many security teams.

## Which should you choose?

Five to twenty engineers on GitHub and Slack, already paying Anthropic or OpenAI, who want small tickets, test gaps and on-call fixes handled in the background: Jiro. [4] [12] A larger organisation on Teams or GitLab that wants ticket events to open sessions and prefers one invoice for agent and model: Devin. [13]

Undecided? Run both against the same repositories for a month; the trial costs nothing for 30 days, needs no card, and comes with five runtimes. [26] Other contenders are ranked in our [list of Devin alternatives](https://jiro.bot/alternatives/devin), and the [Devin-to-Jiro switching guide](https://jiro.bot/switch/devin-to-jiro) maps Knowledge, playbooks, Secrets and sessions onto their Jiro equivalents.

## Jiro at a glance

| Fact | Jiro |
|---|---|
| What it is | A background coding agent: it works in the cloud and returns pull requests for review [16] |
| Made by | Nori (Tilework Inc.), founded by Amol Kapoor, ex-Google Research [48] |
| Agents it runs | Claude Code, Codex, Cursor, OpenCode, pi-acp [2] |
| Whose model bill | Your Claude/ChatGPT login or API key; Cursor key [4]; Your keys, zero token markup [6] |
| Price | Free 30-day trial; Developer $99/mo; Team $250/mo [26] |
| Runtimes | Developer: up to 3; Team: 5 shared; trial: 5 for 30 days [26] [27] |
| Where work starts | Slack, web, Discord, terminal, schedules, webhooks [12] |
| Where it runs | Isolated cloud environment with your repos and tools [9]; Single-tenant per organization [21] |
| Repos | GitHub App (all or selected repos) or a PAT [39] |
| Not to be confused with | Amazon's Kiro (IDE and agent) or Atlassian's Jira (issue tracker) |
| Last verified | 2026-11-06 |

## About the publisher

Jiro is made by Nori (Tilework Inc.), a New York company. Nori was founded by Amol Kapoor, its CEO, who before Nori did AI research at Google on graph neural networks and co-authored MixHop (ICML 2019). [48] [49] Clifford Ressel is Nori's co-founder and CTO. [50] Nori's customers include Corvus and Miravoice. [51] [44]

## FAQ

### Is Jiro cheaper than Devin?

Usually, when the company already pays for Claude or ChatGPT, because Jiro bills a flat $99 or $250 a month for runtimes and passes model usage through without markup. [26] [6] Without existing subscriptions the answer depends on usage, since Devin's credits price tokens at $0.50 in and $2.00 out per million under Adaptive. [7]

### Does Jiro use its own model like Devin does?

No. Jiro hosts your choice of harness, Claude Code or Codex most often, with your own credentials. [2] Devin runs Cognition's agent and routes across several vendors' models plus its own. [5]

### Can I bring my Claude subscription to Devin?

No. Devin can link a personal ChatGPT plan, and that covers GPT requests alone. [8] Jiro accepts a Claude login or a `claude setup-token` token bound to whatever paid Claude plan you hold. [4] [34]

### Do both work from Slack?

Yes. Devin adds Microsoft Teams and two-way thread sync; Jiro adds Discord and a terminal. [41] [13] [12]

### Which one supports GitLab?

Devin does, along with Bitbucket and Azure DevOps. [13] Jiro's git host is GitHub, via its App or a PAT. [39]

### Does either run entirely inside my own cloud?

Jiro's dedicated BYOC deployment runs the session machines in your own AWS account. [23] Devin's dedicated option keeps the Devbox in a Cognition-hosted single-tenant VPC and the brain in Cognition's cloud. [22]

### Is Jiro related to Kiro or Jira?

No. Kiro is Amazon's coding agent and Jira is Atlassian's issue tracker; Jiro is made by Nori.

## Try Jiro

Start the 30-day free trial, no card needed: https://login.norisessions.com/?signup=1&entrypoint=jiro

Or install Jiro's engineering skills into your own agent: `npx nori-skillsets install public/jiro`

## Sources

1. Cognition describes Devin as an autonomous software engineer that runs in the cloud or on your machine and tests its work in its own browser. Source: https://devin.ai/ (checked 2026-11-06)
2. Nori's default first-class Sessions agents are Claude Code, Codex, Cursor Agent, OpenCode and pi-acp. Source: https://docs.noriagentic.com/sessions/reference/supported-agents-and-compute (checked 2026-11-06)
3. Devin Cloud runs Cognition's Devin agent; Devin Desktop can also host other agents that speak ACP. Source: https://cognition.com/blog/introducing-devin-desktop (checked 2026-11-06)
4. Claude Code in Nori accepts an Anthropic API key, a Claude OAuth login or a setup token; Codex accepts an OpenAI API key or Codex OAuth; Cursor Agent needs a Cursor API key; OpenCode and pi-acp take a compatible API base URL, API key and model. Source: https://docs.noriagentic.com/sessions/reference/supported-agents-and-compute (checked 2026-11-06)
5. Devin offers models from Anthropic, OpenAI, Google and Cognition's own SWE family, with an Adaptive option that routes each task to a model automatically. Source: https://docs.devin.ai/cli/models.md (checked 2026-11-06)
6. Nori's comparison table lists any model on your own keys with flat pricing and zero token markup. Source: https://noriagentic.com/#compare (checked 2026-11-06)
7. On Devin's self-serve plans the Adaptive router draws down quota at a fixed $0.50 per million input tokens and $2.00 per million output tokens whichever model it picks, and enterprise accounts have Adaptive switched off until an admin enables it. Source: https://docs.devin.ai/cli/adaptive.md (checked 2026-11-06)
8. On Devin's self-serve Pro, Max and Teams plans a user can link a personal ChatGPT Go, Plus or Pro plan so that requests to OpenAI models bill to that plan, while non-GPT models and cloud machine time still consume Devin quota. Source: https://docs.devin.ai/admin/billing/chatgpt.md (checked 2026-11-06)
9. Each Nori agent works in an isolated cloud environment with your repository, tools, dependencies and services ready to use. Source: https://noriagentic.com/#faq (checked 2026-11-06)
10. Devin's environment is a Linux virtual machine described by a blueprint and saved as a snapshot that every session boots from, and changes made inside a session do not persist back to the snapshot. Source: https://docs.devin.ai/onboard-devin/environment.md (checked 2026-11-06)
11. A Nori organization can define a setup script that installs dependencies and prepares every session's environment. Source: https://docs.noriagentic.com/start/what-can-nori-do#give-agents-a-real-working-environment (checked 2026-11-06)
12. Nori work can start from Slack, the web dashboard, Discord, the Handroll terminal, schedules and webhooks, all reaching the same fleet. Source: https://docs.noriagentic.com/start/what-can-nori-do#start-agent-work-from-the-tools-your-team-already-uses (checked 2026-11-06)
13. Devin connects to GitHub, GitLab, Bitbucket and Azure DevOps repos and takes work from Slack, Microsoft Teams, Linear, Jira, PagerDuty and Pylon. Source: https://docs.devin.ai/integrations/overview.md (checked 2026-11-06)
14. Nori cron triggers run recurring jobs, reminders run once at a future time, and webhooks react to external events. Source: https://docs.noriagentic.com/resources/faq#can-nori-run-tasks-without-a-person-online (checked 2026-11-06)
15. Devin Automations start sessions from schedules, webhooks, and Slack, GitHub, GitLab, Linear, Jira, Pylon and PagerDuty events. Source: https://docs.devin.ai/product-guides/automations.md (checked 2026-11-06)
16. Nori agents can return a pull request, commit, comment or completed task for you to review, merge or send back. Source: https://noriagentic.com/#faq (checked 2026-11-06)
17. Devin opens pull requests and automatically responds to comments on PRs its sessions are working on until the session is archived. Source: https://docs.devin.ai/integrations/gh.md (checked 2026-11-06)
18. Devin splits large changes into stacked pull requests that land bottom-up, resolves conflicts between layers itself and fixes CI across the stack, and stacking works only on GitHub.com repositories. Source: https://docs.devin.ai/work-with-devin/stacked-prs.md (checked 2026-11-06)
19. A Nori skillset is written once and translated into each agent's own files: CLAUDE.md for Claude Code, GEMINI.md for Gemini CLI, copilot-instructions.md for GitHub Copilot and AGENTS.md for the rest. Source: https://docs.noriagentic.com/skillsets/concepts/translation-and-agents (checked 2026-11-06)
20. Devin Skills are SKILL.md files that follow the open Agent Skills standard, read from .agents/skills/ and other repository paths including .claude/skills/, or written on the Customize page at personal, organization or enterprise scope. Source: https://docs.devin.ai/product-guides/skills.md (checked 2026-11-06)
21. Each hosted Nori organization gets a single-tenant broker on its own subdomain. Source: https://docs.noriagentic.com/sessions/concepts/security-and-credentials#organization-isolation (checked 2026-11-06)
22. In Devin's Customer Dedicated Deployment, Cognition hosts the Devbox in a customer-isolated single-tenant VPC reached from your network over AWS PrivateLink or an IPSec tunnel, and the Devin brain always resides in Cognition's cloud. Source: https://docs.devin.ai/enterprise/deployment/overview.md (checked 2026-11-06)
23. Nori hosts Jiro in its own cloud, and a dedicated BYOC deployment runs private EC2 session machines inside customer-controlled AWS infrastructure. Source: https://docs.noriagentic.com/sessions/reference/supported-agents-and-compute (checked 2026-11-06)
24. Devin Outposts, available on Pro, Max and Teams, runs sessions on machines you operate through a self-hosted worker that needs only outbound HTTPS, while planning and inference stay in Devin's cloud. Source: https://docs.devin.ai/cloud/outposts/overview.md (checked 2026-11-06)
25. Nori logs every session and every action, and makes them searchable. Source: https://noriagentic.com/for-security-leaders.html (checked 2026-11-06)
26. Nori's plans start with a free 30-day trial with no card; Developer is $99 a month for one user with up to three persistent runtimes, and Team is $250 a month for multiple users sharing five runtimes. Source: https://noriagentic.com/#pricing (checked 2026-11-06)
27. Nori sizes plans by runtimes, which sleep when idle and wake on demand; the trial runs five for 30 days. Source: https://noriagentic.com/#faq (checked 2026-11-06)
28. Devin's self-serve plans are Free, Pro at $20 a month, Max at $200 a month and Teams at $40 a month per full seat with an $80 monthly minimum, so one seat and two seats both cost $80 a month; usage past the quota is billed as on-demand credits. Source: https://docs.devin.ai/admin/billing/self-serve.md (checked 2026-11-06)
29. Devin Pro and Teams full seats get a daily and a weekly usage quota, Max gets a larger weekly quota with no daily cap, the Free plan gets limited usage plus Devin Review and DeepWiki, and usage beyond quota is paid with on-demand credits that never expire. Source: https://docs.devin.ai/admin/billing/self-serve.md (checked 2026-11-06)
30. Free and Pro allow up to 10 concurrent Devin sessions; Max and Teams have no concurrency cap. Source: https://devin.ai/pricing (checked 2026-11-06)
31. A Devin Teams account holds up to 200 members; full seats cost $40 a month each with a Pro-sized quota, flex seats are free and draw on a shared on-demand credit pool, and when fewer than two full seats are paid the rest of the $80 minimum is charged as prepaid credits. Source: https://docs.devin.ai/admin/billing/self-serve.md (checked 2026-11-06)
32. Cognition retired its Core and Team plans for quota-based self-serve plans on 2026-04-14, billing self-serve overage in dollars instead of ACUs while Enterprise stays on ACUs. Source: https://cognition.com/blog/new-self-serve-plans-for-devin (checked 2026-11-06)
33. Devin Cloud runs sessions on Cognition-hosted machines; Devin CLI and Devin Desktop run locally. Source: https://docs.devin.ai/llms.txt (checked 2026-11-06)
34. The claude setup-token command generates a one-year token tied to a Pro, Max, Ultra, Team or Enterprise plan for machines where browser login isn't available. Source: https://code.claude.com/docs/en/authentication (checked 2026-11-06)
35. Cognition introduced Devin Desktop as the next generation of Windsurf on 2026-06-02. Source: https://cognition.com/blog/introducing-devin-desktop (checked 2026-11-06)
36. Other public ACP registry agents run in Nori only when the ACP registry feature is explicitly enabled, and Gemini was removed from managed Sessions and is rejected by the broker. Source: https://docs.noriagentic.com/sessions/reference/supported-agents-and-compute (checked 2026-11-06)
37. In Nori, one claimed machine serves one active session within the organization's fleet. Source: https://docs.noriagentic.com/resources/faq#is-each-session-isolated (checked 2026-11-06)
38. Devin Secrets store API keys, site cookies and TOTP codes at organization, personal, repository or session scope, and Devin binds each secret only to the command or browser field that needs it rather than exporting it into every shell. Source: https://docs.devin.ai/product-guides/secrets.md (checked 2026-11-06)
39. Nori supports two GitHub credential methods: a GitHub App you install and scope to all repositories or a selected set, or a saved personal access token. Source: https://docs.noriagentic.com/sessions/guides/integrations#github (checked 2026-11-06)
40. Nori's dashboard exposes a catalog of MCP servers for project management, observability, analytics and other tools, and each server's own permissions still apply. Source: https://docs.noriagentic.com/sessions/guides/integrations#managed-mcp-servers (checked 2026-11-06)
41. Mentioning @Devin in a Slack channel starts a session that replies in the thread, a session can sync both ways with its thread, and a code channel dedicates one Slack channel to one session. Source: https://docs.devin.ai/integrations/slack.md (checked 2026-11-06)
42. Mention Nori's bot in a Slack channel to start a session; it replies in a thread, and every reply in that thread continues the same session. Source: https://docs.noriagentic.com/sessions/guides/slack (checked 2026-11-06)
43. Nori connects to Salesforce, HubSpot, Google Sheets, Google Drive, Notion, Linear, Jira, Stripe and Gmail, plus hundreds more. Source: https://noriagentic.com/#faq (checked 2026-11-06)
44. Nori handles more than 25% of Miravoice's merged pull requests, and Miravoice's CTO says it easily saves him five hours a week. Source: https://noriagentic.com/newsletter/2026-09-18-miravoice-case-study.html (checked 2026-11-06)
45. Devin Enterprise's Customer Dedicated Deployment runs the Devbox in a single-tenant VPC, while Devin's brain always stays in Cognition's cloud. Source: https://docs.devin.ai/enterprise/deployment/overview.md (checked 2026-11-06)
46. Claude Max costs $100 a month for five times the Pro plan's usage every five hours and every week; the former Max 20x tier is now sold as Ultra. Source: https://support.claude.com/en/articles/11049741-what-is-the-max-plan (checked 2026-11-06)
47. Anthropic reports that across enterprise deployments Claude Code averages about $13 per developer per active day and $150 to $250 per developer per month, staying below $30 per active day for 90% of users. Source: https://code.claude.com/docs/en/costs (checked 2026-11-06)
48. Nori is led by CEO Amol Kapoor, a former Google Research scientist, and CTO and co-founder Clifford Ressel. Source: https://ai.engineer/speakers/amol-kapoor (checked 2026-11-06)
49. Amol Kapoor's Google-affiliated research includes MixHop (ICML 2019), N-GCN and a 2020 spatio-temporal graph neural network for COVID-19 forecasting. Source: https://scholar.google.com/citations?user=SC_-qB8AAAAJ (checked 2026-11-06)
50. Clifford Ressel is Nori's CTO and co-founder. Source: https://ai.engineer/orgs/nori (checked 2026-11-06)
51. Corvus's CTO saw a production bug at a client dinner, had Nori look into it and deploy a fix. Source: https://noriagentic.com/newsletter/2026-05-19-corvus-case-study.html (checked 2026-11-06)

---

Jiro is a background coding agent by Nori. It is not Amazon's Kiro or Atlassian's Jira.
