> ## Documentation Index
> Fetch the complete documentation index at: https://docs.corbits.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# GTM Workbench

> An AI-assisted, human-in-the-loop go-to-market workspace built on the Corbits agentic platform — turn sales calls, docs, and links into publishable collateral you review at every step.

## What GTM Workbench is

GTM Workbench is an AI-assisted workspace where agents and workflows turn your source material — sales-call transcripts, documents, URLs — into publishable **artifacts**: case studies, one-pagers, emails, LinkedIn posts, and briefs.

It is deliberately **human-in-the-loop (HITL)**. The agents handle analysis and first drafts; you curate, approve, and refine at every stage. This is intentionally not a black-box, fully automated pipeline — you stay in control of what ships.

<Info>
  Workbench is a flagship example of what teams build on the Corbits agentic platform. We run it internally to move our own go-to-market work — so the platform primitives it depends on (tenancy, agent lifecycle, credentials and grants, native workflows, and skills-as-assets) are proven in production, not just documented.
</Info>

It's built for sales and marketing teams who want to turn call insights into usable content quickly, without waiting on a content team.

## Meet Myra, your chief of staff

Every user gets a personal AI agent named **Myra**, framed as a chief of staff and executive assistant. Workbench opens directly into a conversation with her — it's chat-first.

<CardGroup cols={2}>
  <Card title="Parallel threads" icon="comments">
    Run multiple Myra **threads** at once. Each thread is a full agent with its own tools and history — not just a saved transcript — so you can keep separate lines of work going in parallel.
  </Card>

  <Card title="Shared memory" icon="brain">
    Myra's durable memory is shared across all of your threads. What she learns in one chat — standing facts, context, contacts — is available in the others.
  </Card>

  <Card title="Works with your files" icon="paperclip">
    Attach an image or a PDF to a message. Myra reads images directly and understands PDFs through a dedicated file parser, so documents work regardless of her underlying chat model.
  </Card>

  <Card title="Reuses your artifacts" icon="recycle">
    Myra can read a document you or a workflow saved earlier as an artifact, so prior work becomes input for the next task.
  </Card>
</CardGroup>

<Note>
  Alongside Myra, a workspace agent named **Oat** processes call recordings into call-document artifacts, giving your workflows clean source material to build on.
</Note>

## The source-to-artifact model

Workbench follows one product rule: **you choose outcomes, not pipeline topology.** You bring source material, pick the outcome you want, review the decisions that matter, and approve usable artifacts. The internal steps stay hidden.

That model is built from a small, consistent vocabulary:

| Term            | What it means                                                                                                                    |
| --------------- | -------------------------------------------------------------------------------------------------------------------------------- |
| **Source**      | Input material you select — a transcript, a document, a URL, or a prior Artifact reused as input.                                |
| **Offering**    | The product-facing outcome you pick from a catalog or command menu, such as "Create sales collateral" or "Draft LinkedIn posts." |
| **Job**         | One run of a workflow against your selected sources and options.                                                                 |
| **Review Gate** | A human decision point — confirm sources, select findings, approve artifacts, confirm delivery.                                  |
| **Artifact**    | An output produced by a Job. An Artifact can later become a Source for the next Job.                                             |
| **Package**     | A curated group of artifacts you review, export, or deliver together.                                                            |
| **Hook**        | An optional final delivery step — copy or export, draft an email, or draft and schedule a social post.                           |

The visible flow is short and predictable:

<Steps>
  <Step title="Choose your source">
    Select the material a Job should work from — call documents, uploaded files, URLs, or an artifact from earlier work.
  </Step>

  <Step title="Choose an outcome">
    Pick an Offering that describes what you want to produce. You select the outcome; the workflow decides how to get there.
  </Step>

  <Step title="Review findings">
    At a review gate, the Job shows you what it found and asks for the decision that matters — which findings should drive the content.
  </Step>

  <Step title="Approve artifacts">
    Approve, reject, or request refinement on each generated artifact before it counts as done.
  </Step>

  <Step title="Export">
    Copy, download, or hand off approved artifacts through an optional delivery Hook.
  </Step>
</Steps>

<Info>
  Every Job streams its progress in a single, generic run console. There is no bespoke per-workflow screen to learn — the same review surface handles confirming sources, selecting findings, and approving artifacts across every outcome. When a Job reaches a review gate, it pauses and waits for your approval before continuing.
</Info>

## Skill Library

Upload, browse, and version reusable AI instruction sets — the prompts, personas, and procedures that shape how agents respond. Inspect a skill's files, review its version history, and restore any prior version. Attach a skill to an agent to change its behavior.

## Built on the Corbits platform

Workbench doesn't reinvent the hard parts. It relies on the Corbits agentic platform for the primitives every serious agentic product needs, so the team can focus on the go-to-market experience instead of infrastructure.

<AccordionGroup>
  <Accordion title="Tenancy and agent lifecycle">
    The platform provisions each user's personal Myra instance and manages the lifecycle of every agent and workspace worker. Workbench doesn't build its own identity or agent-runtime layer.
  </Accordion>

  <Accordion title="Credentials and grants">
    Inference and tool credentials are stored and resolved by the platform, and every tool call is authorized against a grant. Members never enter API keys, and access is scoped by the platform rather than a hand-rolled permission model.
  </Accordion>

  <Accordion title="Native workflows">
    Workflows are deployed definitions that run on the platform's native workflow runtime — durable runs, review-gate signals, and event logs included. Adding a new workflow is a new package and a push, not a rewrite of the app.
  </Accordion>

  <Accordion title="Skills as assets">
    The Skill Library is backed by the platform's asset substrate, which owns storage and versioning. Workbench never reimplements how skills are stored or versioned.
  </Accordion>
</AccordionGroup>

<CardGroup cols={2}>
  <Card title="Platform overview" icon="layer-group" href="/platform/overview">
    See the agentic platform Workbench is built on.
  </Card>

  <Card title="Credentials and guardrails" icon="shield-check" href="/platform/guardrails">
    How credentials, grants, and delivery capabilities are governed.
  </Card>
</CardGroup>

## Why teams use it

<CardGroup cols={2}>
  <Card title="Fast" icon="bolt">
    Select your sources, pick an outcome, and get draft collateral in minutes.
  </Card>

  <Card title="Reviewable" icon="user-check">
    Every stage is human-approved. No black-box automation deciding what ships.
  </Card>

  <Card title="Resumable" icon="rotate-right">
    Jobs and sessions are saved, so you can step away and come back to iterate.
  </Card>

  <Card title="Exportable" icon="file-export">
    Approved artifacts are ready to copy, download, or deliver through a Hook.
  </Card>
</CardGroup>