Core Concepts Open-Core

Intutic introduces a handful of key abstractions you'll encounter throughout the platform. This page is your glossary — bookmark it and come back whenever you need a refresher.

What you'll learn

• The organizational and runtime building blocks of Intutic
• How policies, enforcement, anomaly detection, and scoring fit together
• The role-based access model and budget tiers

Workspaces

A workspace is the top-level organizational unit in Intutic. Everything — harnesses, SOPs, traces, budgets, and team members — lives inside a workspace.

• IDs use the wk_ prefix (e.g., wk_abc123)
• On the Free and Pro plans you get one workspace; Team and Enterprise support unlimited workspaces
• Each workspace has its own virtual API key (vk_*) that the proxy uses for authentication

One workspace per repo

Most teams map one workspace to one code repository. This keeps governance rules scoped to the project they apply to.

Harnesses

A harness is any AI coding agent that Intutic governs. Intutic currently supports 41 harnesses — 40 auto-detected and config-synced by intutic init/intutic connect (some write directly into a generated hook file, others write .env.intutic pointing at a dedicated SDK-side gate (@intutic/gate / intutic-clawde) that lives in your own code), plus 1 that is operator-deployed rather than repo-detected (see the bridge-gated row below):

Category	Harnesses
IDE agents	Cursor, Windsurf, Continue, Cline, Roo Code, GitHub Copilot
CLI agents	Claude Code, Aider, Codex, Goose, Pi, Grok Build, Muse Code, dsh (preview)
Platform agents	Antigravity, OpenHands, n8n, Claude Desktop, Open WebUI
Specialized	OpenClaw, Hermes, LangGraph
Orchestrators (delegate to already-gated harnesses)	Spotify Xirp, DoorDash Agentic Orchestrator, AWS Bedrock AgentCore Runtime
SDK-gated frameworks (@intutic/gate / intutic-clawde; .env.intutic points at the SDK gate instead of a generated hook file)	LangChain, CrewAI, AutoGen, AG2, Google ADK, OpenAI Agents SDK, Pydantic AI, smolagents, AWS Strands Agents, Mastra, Vercel AI SDK, eve, TrueForge (embedded), AI SDK Harness, AI SDK Workflow
Bridge-gated (out-of-process Intutic-operated service; not auto-detected by intutic init — operator-deployed instead)	TrueForge (standalone/hosted server — services/trueforge-bridge)

The intutic init command auto-detects which harnesses are present in your repo and writes governance config into each one's native config file. See How It Works for details on per-harness routing.

A separate, smaller set of server-side platform integrations — QM, Anthropic Managed Agents, and AWS Bedrock AgentCore Gateway — call Intutic directly over HTTP as part of their own contract. They have no HarnessType and are not detected by intutic init; see the Integrations Hub for details.

SOPs (Agent Guidelines)

Standard Operating Procedures are the policy documents that tell your agents what they can and cannot do. Think of them as enforceable coding standards for AI.

Each SOP has:

• Title and markdown content — the human-readable rules
• Risk tier — LOW, MEDIUM, HIGH, or CRITICAL
• Complexity tier — the task complexity level this SOP targets
• Dependencies — other SOPs this one builds on

SOP lifecycle

SOPs follow a 7-state lifecycle:

State	Meaning
DRAFT	Initial authoring — not enforced yet
PENDING_REVIEW	Submitted for team review
GENERATED	Auto-generated from observed agent patterns
HYPOTHESIZED	Proposed rule being tested against real traffic
REFINED	Iteratively improved based on feedback and data
VALIDATED	Active and enforced by the proxy
INVALIDATED	Retired or superseded by another SOP

Only SOPs in the VALIDATED state are actively enforced. Learn more in Standard Operating Procedures.

Enforcement Actions (PCAS)

The Policy Compliance and Action System evaluates every LLM request against your active SOPs and applies one of four actions:

Action	Effect	Example scenario
BYPASS	Request passes through unmodified	Fully compliant with all policies
ENHANCE	Request is enriched (prompt injection, context added)	SOP suggests adding security context to the prompt
HIJACK	Request is rerouted to a different model	Downgrading gpt-4o to gpt-4o-mini for a simple task
KILL	Request is blocked entirely	Budget exceeded, unauthorized tool call, or policy violation

HIJACK decisions require review

When PCAS applies a HIJACK action, the decision is routed to the human review queue so an administrator can approve or reject it.

Traces

A trace is the audit record of a single LLM request. Every request that flows through the Intutic proxy produces a trace (prefixed tr_).

Each trace captures:

• Model used and token counts (input + output)
• Cost in USD
• Enforcement action applied (BYPASS / ENHANCE / HIJACK / KILL)
• Compliance score — how well the request matched active SOPs
• Token utility — classified as USEFUL or WASTED

Traces are the foundation for cost tracking, anomaly detection, and compliance auditing.

Reasoning/Thinking Tokens

Reasoning tokens (or thinking tokens) are special, non-content tokens generated internally by advanced reasoning models (e.g. Claude 3.7 Sonnet thinking mode, OpenAI o1/o3 series) during deep-thinking cycles.

• Intutic's proxy automatically extracts these tokens (token/reasoning_extractor.rs) to report actual raw vs. reasoning cost proportions in the trace ledger.
• Tracking reasoning tokens helps teams evaluate where agents spent computation time vs. where they output final code structure.

Token Waste Classification

The Intelligence Engine classifies trace data to identify inefficient token consumption. wastePatternService.ts computes two waste patterns, both derived from columns that exist on execution_traces, and each carries a confidence reflecting how it was derived — so the UI never presents an inference as a measurement:

1. Context bloat (measured, confidence 1.0) — raw input tokens minus compressed input tokens: context the compactor had to strip before the request was billed.
2. Oversized prompt (heuristic, confidence 0.6) — traces whose raw input exceeds 3× the workspace median, with the excess over the median attributed as waste. A legitimately large task looks the same, hence the reduced confidence.

Traces flagged with high waste metrics trigger automated configuration optimizations via the SkillOpt feedback loop.

Anomaly Detection (ARE)

The Autonomous Reasoning Engine monitors agent sessions in real time and flags suspicious behavior across 12 anomaly types:

Anomaly	What it catches
TOOL_ABUSE	Excessive or inappropriate tool calls
TOKEN_WASTE	Inefficient token usage patterns
LOOP_DETECTED	Agent stuck in a retry/repeat loop
UNAUTHORIZED_TOOL	Calling tools outside the allowed set
DATA_EXFILTRATION	Attempting to leak sensitive data
PROMPT_INJECTION	Malicious prompt manipulation
HALLUCINATION	An agent still working for a parent that is gone — its results have nowhere to go
SCOPE_VIOLATION	Operating outside the defined task scope
BUDGET_BREACH	Exceeding the allocated session budget
SPAWN_BUDGET_BREACH	Sub-agent spawning over limits
WORKFLOW_BUDGET_BREACH	Multi-step workflow over budget
WORKFLOW_GOAL_DRIFT	Workflow deviating from its stated objective

When the ARE flags an anomaly, it can trigger a KILL enforcement action and open a governance incident.

Trust Scores

Every agent session receives a trust score — a numerical reliability rating that tracks how well the agent follows governance rules over time. Trust scores factor into enforcement decisions: a session with a declining trust score may trigger stricter PCAS actions.

Compliance Scores

Each trace receives a compliance score indicating how closely the request aligned with active SOPs. High compliance scores mean the agent is working within policy. Low scores trigger review and may feed back into SOP refinement.

Budget Tiers

Budget tiers control how much each developer can spend on LLM calls. They map to seniority levels:

Tier	Intended for
JUNIOR	Junior developers — lowest budget ceiling
SENIOR	Senior developers
STAFF	Staff engineers
PRINCIPAL	Principal engineers — highest budget ceiling

Exceeding your tier's budget triggers a BUDGET_BREACH anomaly and a KILL enforcement action. Budget caps are enforced per developer session.

How it all fits together

Harnesses → Proxy Gateway → PCAS (evaluates SOPs) → Enforcement Action
                                    ↓
                              ARE (anomalies)
                                    ↓
                        Traces → Compliance Scores → Trust Scores

Your SOPs define the rules. PCAS enforces them. The ARE watches for anomalies. Traces record everything. Scores summarize it all.

Next steps

• Getting Started — install the CLI and set up your first workspace
• How It Works — deep dive into the architecture
• Custom Filters (WASM) — custom tool-call filtering policy hooks
• CLI Reference — command line configuration and diagnostics