# Agents that learn from your team

Most AI products give you a thumbs-up button. The rating goes somewhere you
cannot see, changes something you cannot name, and you find out whether it
worked by waiting to see if the mistake happens again.

Karmaflow.ai trains differently. Someone on your team highlights the exact words
an agent got wrong, types what is actually true, and gets back a **receipt**
naming what changed — a concept in your knowledge base, a prompt change filed
against an agent, or an honest "that was specific to one conversation, nothing
was saved." The correction is versioned, attributed, and revertible.

## What It Covers

**Correction where the mistake happened.** Any agent-authored text is
trainable in place — voice call transcripts, chat sessions, SMS threads, sent
email (subject and body as separate targets), task-agent output, and agent
activity surfaced on CRM records. The gesture is identical on all of them:
drag-select, click the chip, say what is true.

**Routing that admits three answers.** An AI reads each correction and decides
where it belongs — a durable business fact, a change to how an agent speaks,
or something true only of that one conversation. It is allowed to conclude
"nothing should change here", and it says so rather than quietly writing
something.

**A knowledge base you can read and undo.** Corrections that become facts land
in the **Tenant Brain**, your workspace's knowledge in the Open Knowledge
Format (OKF). Every concept carries citations, a revision history that
separates *written* from *published*, side-by-side **Compare**, and a
**Restore** that stages an old revision as an unpublished edit rather than
silently swapping what your agents read.

**Autonomy you set, and can audit.** Governance settings decide how much
publishes without a human — from reviewing everything, through publishing only
what a proposer has earned trust to publish, up to auto-publishing verified
high-confidence knowledge with a window in which one click reverts it. Every
surface reports which of those actually happened instead of promising a review
your settings will not perform.

**A second plane for behaviour.** Feedback about *how* an agent speaks goes to
**the Curator** — an AI that reads the feedback against the transcript and the
agent's current prompt and proposes bounded edits. It is allowed to disagree.
In our own testing it declined a style correction as insufficiently grounded in
the transcript and proposed no changes.

**A quality stream underneath all of it.** Message feedback, whole-interaction
feedback, CSAT, session audits, performance scores, ticket insights and
not-durable verdicts land in one stream with sentiment and per-agent
attribution, feeding both the Curator and the knowledge distiller.

```mermaid
flowchart TD
    subgraph S["Where agents work"]
        V["Voice calls"]
        C["Chat + SMS"]
        E["Sent email"]
        T["Task runs"]
        R["CRM activity"]
    end
    S --> H["Someone highlights the exact words<br/>and types what's actually true"]
    H --> J{"What kind of<br/>correction is it?"}
    J -->|"A durable business fact"| K["Tenant Brain — cited,<br/>versioned, revertible"]
    J -->|"How the agent speaks"| P["The Curator proposes<br/>a bounded prompt edit"]
    J -->|"True of one conversation"| N["Noted and closed —<br/>nothing published"]
    K --> G["Governance decides:<br/>publish now, or queue for review"]
    P --> A["A reviewer ticks the edits<br/>they accept, then applies"]
    G --> Q["Every agent reads the<br/>corrected knowledge"]
    A --> Q
    K --> RC["A receipt on the original<br/>message, naming what changed"]
    P --> RC
    N --> RC
    Q --> S
```

## Why Teams Use It

**The people who spot mistakes are the people who can fix them.** Training
needs no permission at all. The rep reading the transcript does not file a
ticket for an admin — they correct it where they found it. Reviewing and
publishing stay permissioned; noticing does not.

**Nobody has to learn the knowledge base.** Correcting an agent does not
require knowing which concept holds the fact, or what a concept is. The AI
finds where the fix belongs.

**Corrections stop being a matter of faith.** Every one ends in a named
outcome. "Became knowledge — `policies/service-levels.md`" is checkable; a
thumbs-up disappearing into a dataset is not.

**One mistake is fixed once.** A fact corrected on a voice call is read by the
chat agent, the email strategy, and the task agent from that point on. The loop
compounds across channels rather than per-agent.

**Members contribute without being able to break anything.** A member's
correction always lands as a draft for review. That is what makes it safe to
open training to the whole workspace.

## Business Outcomes

| What changes | Why it follows |
|---|---|
| Wrong answers stop repeating across channels | The correction lands in shared knowledge every agent reads, not in one agent's prompt |
| Corrections come from the front line, not a backlog | No permission gate on training; no ticket to file |
| A bad correction is recoverable | Versioned revisions, Compare, and a Restore that stages rather than swaps |
| Style drift is handled separately from facts | Behaviour feedback routes to the Curator and the agent prompt, never into your knowledge base |
| Autonomy can increase without losing the audit | Auto-published changes are listed for 30 days with one-click revert while the window is open |
| Your knowledge base stays clean | One-off details are judged not durable and deliberately not saved |

## What's Different From a Thumbs-Up Dataset

| | Rating-only feedback | Karmaflow.ai training |
|---|---|---|
| What you point at | A whole response | The exact words, quoted back to you |
| What you say | Good / bad | What is actually true, in plain language |
| What you get back | Nothing | A receipt naming the concept, the prompt change, or the decision not to change anything |
| Where it goes | An opaque dataset | A named, cited concept in your own knowledge base |
| Can you undo it | No | Version history, Compare, Restore, and revert-in-window |
| Who may do it | Usually admins | Anyone in the workspace; publishing stays permissioned |
| Portability | None | Open Knowledge Format — the knowledge is yours to export |

Ratings still exist and are still useful — a bare 👍 or 👎 is one click and is
counted as signal. They are the floor, not the ceiling.

## Governance and Trust

- **Training is unpermissioned; publishing is not.** Reviewing the quality
  stream needs `quality:events:read`; promoting, dismissing and changing the
  sharing setting need `quality:events:manage`; publishing or rolling back
  knowledge needs `knowledge:brain:manage`, and changing autonomy needs
  `knowledge:brain:govern`.
- **Nothing is erased.** A rollback is recorded as a new revision, with both
  the change and the undo visible in history.
- **Publishing a contradiction is deliberate.** When a rollback would
  contradict a live claim, a confirmation names the claim and records that you
  published anyway, against your name.
- **Pattern sharing is a choice.** A workspace-level checkbox controls whether
  anonymised quality *patterns* help improve the platform. Only pattern counts
  and PII-scrubbed snippets ever leave the workspace — never contact data, ids,
  transcripts, or feedback threads. Turned off, the workspace is skipped
  entirely.

## Learn More

- **[Training your AI agents](/help/knowledge/training)** — the hub: what
  training is, who can do it, and how outcomes are decided.
- **[Your first correction, step by step](/help/knowledge/training-first-correction)**
  — one complete worked example, every click shown.
- **[Where you can train](/help/knowledge/training-everywhere)** — every
  surface, and what deliberately cannot be trained.
- **[What happened to your feedback](/help/knowledge/training-outcomes)** —
  every receipt explained.
- **[Reviewing what your team teaches](/help/knowledge/training-reviewing)** —
  the reviewer's side, including undo and autonomy.
- **[Quality Events and the Curator queue](/help/knowledge/training-curator)** —
  working the stream and the per-agent review workflow.
- **[Brain Browser walkthrough](/help/knowledge/overview)** — operating the
  knowledge base your corrections feed.

Related: [CRM](/help/crm/overview) for the record memory agents read from, and
[Helpdesk](/help/helpdesk/overview) for the same governance model applied to
support.

[Sign in to Karmaflow.ai](https://omni.karmaflow.ai/auth/login)