Meet the crew
OG the AI developer, QA the AI tester, Oracle for backlog context and P.Chief for your inbox: what each one does and how to talk to it in Slack.
Your awk team ships with four specialist awks (agentic workers): AI developers and testers that build and test your work items, with Oracle for backlog context and P.Chief for your inbox. Each awk has a distinct role, its own set of tools, and a clear boundary on what it can and cannot do.
Some of those limits are technical: a role with read-only access is
restricted from writing. Others are the role's job plus an approval step.
Merging a pull request, pushing to main and force-pushing wait for a
person every time, whichever awk proposes them; opening a pull request
waits too, unless a person on your team in the thread has chosen to approve them all (see
Gated actions).
AWK OG — the engineer
Takes work items, writes code, runs tests, reviews the change, opens the pull request and, once you approve, merges it. Hands off to QA to test the build, if you ask for independent QA.
What OG connects to: GitHub, Jira
Example queries:
@OG-Awk pick up PROJ-318
@OG-Awk build me a /signup endpoint with email validation
@OG-Awk refactor the auth module to use JWT
@OG-Awk what's the status on that PR?
What OG can do: Read Jira tickets, write code, create branches, run tests, put the change through a code review, comment on issues, transition Jira statuses. Open the pull request and merge it, with your approval in Slack: a merge asks every time, and opening one asks unless you've chosen to approve them all in that thread. Spin up a running instance and share a live, sign-in-protected preview URL.
What OG doesn't do: Read or send your email. OG isn't connected to it.
AWK QA — the tester
Checks the build does what the work item asked. Turns the requirements into test cases, runs them with fresh eyes, and flags regressions and security risks. Sends the work back to OG when it doesn't pass, and passes it when it does. OG then finishes the work and, once you approve in Slack, merges the pull request. Ask QA to review a pull request's code and it does that too, with inline comments.
What QA connects to: GitHub, Jira
Example queries:
@QA-Awk review PR #419
@QA-Awk what regressions could this change cause?
@QA-Awk run the integration tests on the feature/auth branch
What QA can do: Check the build against the work item's acceptance criteria. Read diffs, run checks, review a pull request's code when you ask and comment on it, flag issues to the team. Capture and share screenshots and video recordings. Produce test spreadsheets with QA findings and links to artifacts.
What QA doesn't do: Build new features or fix the code it is testing. Its job is to verify. It reads code and comments on PRs, and it commits test code of its own where the work needs it (a test script or a stub, for example). Fixes to the feature itself go back to OG. Opening and merging the pull request is OG's job, not QA's. QA does not own the work item's context or dependency map — that's Oracle.
AWK Oracle — the context oracle
Knows every ticket, why it exists, and what depends on it. Maps relationships across the backlog. Surfaces blockers and dependency chains before you ask.
What Oracle connects to: Jira, GitHub, Slack
Example queries:
@Oracle-Awk what's blocking the auth work?
@Oracle-Awk summarize the sprint backlog
@Oracle-Awk which tickets depend on PROJ-200?
@Oracle-Awk what changed in the payments module this week?
What Oracle can do: Read tickets, map dependencies, search across your backlog and repos, trace relationships, summarize context.
What Oracle cannot do: Write code, open PRs, or modify tickets.
AWK P.Chief — your personal chief
One per user, DM-only. Lives in your inbox and calendar. Drafts replies in your voice. Schedules things across time zones. Escalates what matters; silent on what doesn't.
What P.Chief connects to: Gmail or Outlook, Google Calendar or Microsoft Calendar
Example queries (via DM):
Draft a reply to Sarah's email about the Q3 timeline
Block 2 hours for deep work tomorrow morning
What's on my calendar this week?
Reschedule my 1:1 with Alex to Thursday
What P.Chief can do: Read and draft emails, manage calendar events, schedule across time zones, summarize your inbox.
What P.Chief cannot do: Access other users' email or calendars, make purchases, or access code repositories.
See P.Chief setup to connect your email and calendar.
Attachments / rich media
Don't describe it — just attach it. When you drop a file into a Slack thread (or DM), the agentic workers read it directly. No transcribing a stack trace by hand, no retyping what a screenshot says.
Images — screenshots, diagrams, UI mockups, whiteboard photos. The agentic worker reads on-screen text, error messages, and layout. Paste a screenshot of a failing build and ask OG to fix it.
@OG-Awk here's the error I'm getting [screenshot]
PDFs — specs, design docs, exported tickets, contracts. The agentic worker reads the document text, with tables kept intact, and works from it the same way it works from a message.
@Oracle-Awk the requirements are in this PDF — which tickets does it map to?
Audio — voice notes and recordings (mp3, wav, m4a, and similar). The agentic worker listens to the recording and works from what's said; for non-speech audio it notes what it hears. Record a voice note instead of typing a long task.
@OG-Awk [voice note describing a feature]
Video — short screen recordings and clips (mp4, mov, and similar, up to 20 MB). The agentic worker takes in both the spoken narration and what happens on screen. The headline use case is QA bug reports: a QA teammate (or AWK QA) records a screen capture of a defect — the spoken narration, the on-screen error, the repro steps, the moment it breaks — and hands the recording straight to the developer awk, which watches it to understand the problem. No writing the bug up by hand. Video is off by default (it uses the most credits) — a team admin turns it on per team (see below).
@OG-Awk [screen recording of the bug] — what's going wrong here?
Images, PDFs, and audio work today across both Slack and DMs; video works too, enabled per team.
Per-team media controls
Admins control which media types each team can use, to manage cost. From the team's settings in the console you can turn images, PDFs, audio, and video on or off per team. Images, PDFs, and audio are on by default; video is off by default (it uses the most credits) and is switched on here when a team wants it.
Models
Agentic workers run on frontier LLMs from three providers:
- →Anthropic — Claude
- →OpenAI — GPT
- →Google — Gemini
Model selection is automatic based on task requirements.
All LLM access uses providers' commercial APIs (Anthropic, OpenAI, and Google) under business terms that prohibit training on your data. Your code, work items, and email content are never used to train the providers' models. See the FAQ for more on data privacy.
How they work together
The agentic workers operate as a team. A typical flow:
- →OG picks up a work item, from Jira or from a Slack message, and starts building
- →OG reviews the change, opens a PR and, when independent QA is requested, hands off to QA
- →QA tests the build against the work item and sends bugs back to OG; once it passes, OG merges the PR when you approve in Slack
- →Oracle tracks the ticket through the backlog and surfaces blockers
- →P.Chief keeps your inbox and calendar clear so you can focus
Handoffs between agentic workers are always explicit — you see them happen in your Slack threads. No agentic worker silently delegates to another.