Skip to content

Agents

Agents with a job title and a paper trail.

Each agent has one job, a catalogue ID and a set of tools. You watch the fleet, approve what matters, and read the trail of anything it did.

Catalogue

Agents named for the job they do.

A job title and a catalogue ID, never a human name or face. These five are examples of what a pilot can start with.

Support Agent

LMN-2041
Example

Answers tickets, looks up orders and drafts replies.

tickets.readorders.getpolicy.search

Waits for a person: Refunds and credits

Billing Agent

LMN-2077
Example

Handles invoices, failed payments and plan changes.

invoices.getpayments.retryplans.change

Waits for a person: Any refund or plan downgrade

Research Agent

LMN-2110
Example

Reads your data and writes the weekly summary.

warehouse.querydocs.searchreport.write

Waits for a person: Sending a report outside the team

Code Review Agent

LMN-2153
Example

Reviews pull requests and runs the tests.

repo.readtests.runpr.comment

Waits for a person: Merging or pushing to main

Onboarding Agent

LMN-2190
Example

Sets up new accounts and sends the welcome sequence.

accounts.createemail.draftcrm.update

Waits for a person: The first email to each account

The console

The fleet, the sessions and one agent’s trail.

The selected agent shows its approved plan, each traced step, the approval gate, its receipt and a live timer. Press Stop and it stops.

Sample data throughout. Example

Open the live Inferstack Console

Under the hood

The session layer: four mechanisms.

Long agent sessions resend the same context again and again. The session layer is built so they don’t pay for it twice.

  1. 01

    Keeps each session on its cache

    Requests from one agent session go to the GPU that already holds its KV cache, so old context isn’t computed again.

    KV cacheSession routing

  2. 02

    Lays out prompts so they stay cacheable

    Stable parts go first and new turns go last: system prompt, tools, repo map, then turns. One changed token early in the prompt breaks the cache for everything after it.

    Prefix cachingPrompt layout

  3. 03

    Picks a model for each step

    Three policies: cost, balanced and quality. Under balanced, chat and extraction go to a small model; code and reasoning go to a large one.

    Step routingSmall + large models

  4. 04

    Hands the session over on a switch

    The session lives in a log that no single model owns, so a new model can pick it up where the last one stopped.

    Session logModel handoff

What happens when you switch models mid-session

  1. 1Freeze

    Stop at a clean turn boundary.

  2. 2Compact

    Fold old turns into the session log, keeping the plan, decisions and open files.

  3. 3Render

    Write the log in the new model’s chat template and tool format.

  4. 4Warm up

    One prefill fills the new model’s cache.

  5. 5Check

    A short probe confirms the new model knows the plan.

  6. 6Go on

    The agent continues from the same turn.

Put one agent on one real workflow.

A pilot is one agent, set up with us, on your own work. You keep the receipts.