How it works

Anatomy of a Squidgy agent: executable skill files, not chatbots over docs.

Every Squidgy agent is an executable skills file: structured knowledge that an AI agent can act on, not just retrieve. Here's how that's built — and why it's a different category from RAG.

The primitive

Five components.
One executable bundle.

Every agent on Squidgy is composed from the same primitive — five files that together describe what the agent does, how it does it, and what it knows. Versioned like code. Inspectable like a contract. Runnable like a process.

01Step

YAML config

skills/{agent}/config.yaml

Capabilities, tools the agent can call (calendar, CRM, email, custom APIs, MCP servers), channels it deploys to, eval settings, deployment policy. The contract.

Example

name: maya
role: accountability_coach
tools:
  - google_calendar
  - hubspot
  - slack
deploy_to: [embed, slack]
eval_suite: maya_v3
human_approval:
  - send_to_customer
02Step

System prompt

skills/{agent}/system-prompt.md

Voice, rules, escalation paths, behavioural guardrails. Written in plain English by Ace from your description, refined as the agent learns.

Example

You are Maya, an accountability coach for fitness professionals…
NEVER send a customer message without human approval.
ESCALATE to founder@example.com if a client mentions cancellation.
Voice: warm, concise, action-oriented. Use the customer's first name.
03Step

Knowledge base

skills/{agent}/kb/

Your facts, policies, products, examples — your training corpus and your operating reality. RAG-grounded so answers come with citations to source documents.

Example

kb/policies.md     # cancellation policy, refund policy
kb/programs.md     # 8-week / 12-week / lifetime program details
kb/voice-guide.md  # 12 example messages in your tone
kb/escalation.md   # when to hand to a human, who to hand to
04Step

Workflow

n8n/{agent}_workflow.json

The orchestration — handoffs to other agents, branching logic, human-approval gates, retry policies. Runs on N8N under the hood; visible to you, executable by the agent.

Example

Trigger: customer message →
  Pia router → routes by topic →
    Maya draft reply →
      Human approval queue →
        Send via Slack/email →
          Log outcome → eval
05Step

Deployed agent

live across selected channels

Live across whichever channels you chose — embed widget, Slack, Teams, Roam, voice. Eval suites monitor for regression. Marketplace listing optional. Your skill files keep running as updates ship.

Example

Channels: web embed, Slack DM, Slack channel
Eval pass rate: 94% (target: ≥90%)
Marketplace listing: Certified · 4.8★ · 47 active customers
Last KB update: 2 days ago (cancellation policy)
The contrast

Search over docs (RAG)
vs. executable skill files.

Both approaches use large language models. Both ground answers in your data. But they answer different questions. RAG helps a model retrieve. Executable skill files let an agent act.

DimensionSearch over docs (RAG)Executable skill files (Squidgy)
Primary jobRetrieve relevant snippets and compose an answerAct on the customer's behalf — book, send, qualify, decide
Knowledge formatDocuments indexed for semantic searchYAML + system prompt + KB + workflow — structured for execution
Inspectable?Black-box composed answerEvery component diffable; agent state recorded
VersioningDocument-level (re-index)File-level (skill files versioned like code)
Multi-step workSingle Q→A turnWorkflows with handoffs, branches, human-approval gates
Multi-agent teamsOne bot per docs corpusRouter (Pia) dispatches to specialists, agents hand off
Tool/action capabilityLimited — usually "answer only"Native — agent calls tools to actually do the work
Learning loopAdd a doc to the indexEval suite catches regressions; experiments graduate to playbooks
When you outgrow itCustomer asks for an action — you build a separate workflowAgent already does the action; you ship the next one
DefensibilityAnyone can re-build with the same docsYour skill files encode HOW you operate — that's the moat

RAG and executable skill files aren't competitors — Squidgy uses RAG inside its knowledge base. The difference is the layer above: RAG-only systems retrieve and stop; Squidgy agents retrieve, decide, act, and continue.

Team orchestration

One agent rarely does the whole job.

Real workflows need specialisation, handoffs, and shared state. On Squidgy that's built in — the orchestration layer is part of the platform, not something you wire up.

Pia router

A router agent receives every inbound request and dispatches it to the specialist best fit for the job. Your specialist agents stay focused — Pia handles the air-traffic-control.

Agent handoffs

When one agent needs to pass to another ("this is a billing question, route to Marcus"), the handoff carries the conversation state. The next agent picks up cold-start free.

State management

Per-user persistent memory + per-conversation context. Agents remember commitments across sessions. Privacy is enforced — no cross-user leakage by design.

The learning loop

Every iteration compounds.

Skill files aren't static. The same versioning that makes them inspectable makes them improvable — by you, by your team, by the platform. The loop has three steps.

01

Audits

Eval suites run on every change. Production traces are sampled, scored, and flagged when behaviour drifts. Customer feedback (thumbs, escalations, refund signals) feeds back into the audit.

02

Experiments

When the audit surfaces a problem or opportunity, experiments are scoped: a new prompt variant, a tweaked workflow, an updated KB. Each experiment has a hypothesis, a metric, and a result.

03

Playbooks

When an experiment wins twice, it graduates to a playbook — codified into the skill file or template, reusable across agents. The next builder benefits without rediscovering the lesson.

Distribute

Built once. Deployed everywhere.

The same executable skill files run wherever your customers are — without rebuilding per channel. Channel adapters handle the surface; your skill file is the source of truth.

Embed widget — one script tag, any site
Slack — DM, channel, slash commands
Microsoft Teams — same agent, native to Teams
Roam — for organisations on Roam Research
Voice channels — phone, web voice, voice-platform integrations
White-label apps — vertical brands like Fanatiq, YEAA, Handled
Marketplace listing — others can install your agent and pay you per use
Custom (MCP-compatible) — any MCP-aware client can talk to your agent
Frequently asked

About the structured-knowledge approach.

What is a company brain?+

A company brain is the structured, machine-executable record of how a business actually operates — its skills, workflows, knowledge, and decisions — packaged so AI agents can act on it directly. It's distinct from a knowledge base or RAG system: a knowledge base helps humans (or chatbots) search documents; a company brain gives agents the operating instructions to do the work themselves.

How is Squidgy different from RAG / chatbots over documents?+

RAG retrieves snippets from your documents and feeds them to a model that composes an answer. Squidgy agents are built from executable skill files — versioned YAML configs, system prompts, knowledge bases, and workflows that the agent runs. RAG answers questions about your company. Squidgy agents do work on behalf of your company. Different jobs.

How do AI agents share knowledge across a team?+

On Squidgy, agents are coordinated by an orchestrator (we call ours Pia, a router agent). Agents hand off conversations to each other, share state, and follow shared workflows. Knowledge bases are scoped per agent or shared across the team. Every handoff is recorded so the next agent picks up where the last one left off — no asking the customer to repeat themselves.

What's an executable skill file?+

It's a versioned bundle of everything an agent needs to do its job: a YAML config (capabilities, tools, integrations), a system prompt (voice, rules, escalation), a knowledge base (your facts, policies, examples), and a workflow (the multi-step orchestration). Together they're executable — the agent runs them, doesn't just retrieve from them. Inspectable, diffable, exportable, and never a black box.

Why does this matter for defensibility?+

Two reasons. First: your company brain is the part competitors can't copy — the specific way YOU run YOUR niche. Second: structured-knowledge agents compound. Every iteration improves the skill files; every new agent benefits from the team's shared workflows. RAG over docs gives you a search tool. Executable skill files give you an operating system.

Can I export my agent and its knowledge?+

Yes — explicitly, by policy. Skill files (YAML + system prompt), knowledge bases, workflows, and customer data are all exportable on demand. Squidgy is a platform, not a lock-in.

Do I need to know what YAML or a workflow is to use Squidgy?+

No. The platform handles all the structure for you — you describe the agent in plain English to Ace and it generates the underlying skill files. The structure exists so engineers, ops teams, and the platform can inspect, diff, and improve agents over time. You see plain-English summaries; engineers (or future-you) can read the underlying YAML if they want.

Ready to build one?

Apply for the Agent Builder early-access cohort. Hands-on onboarding included.