POST /plan {"provider": "linear", "intent": "create urgent bug assign to me label backend priority high due next friday"}

Agents shouldn't have to reason about how to work in software.

Agents call Unaka's /plan endpoint — what to do and in which tool — and get back a fully-formed, deterministic execution spec in under a second.

Request access
What /plan returns
{
  "plan_id": "plan_abc123",
  "provider": "linear",
  "workflow": "createIssue",
  "status": "ready",
  "plan": {
    "steps": [{
      "action": "create_issue",
      "object": "issue",
      "inputs": {
        "team_id": "36824a37-...",
        "title": "Login timeout bug",
        "priority": 1,
        "dueDate": "2026-04-11T00:00:00Z",
        "assignee_id": "0abb0e37-..."
      },
      // execution spec — the core differentiator
      "execution": {
        "method": "POST",
        "endpoint": "https://api.linear.app/graphql",
        "headers": {
          "Authorization": "{{LINEAR_API_KEY}}",
          "Content-Type": "application/json"
        },
        "body": {
          "query": "mutation CreateIssue($input: IssueCreateInput!) { issueCreate(input: $input) { success issue { id identifier } } }",
          "variables": {
            "input": {
              "teamId": "36824a37-...",
              "title": "Login timeout bug",
              "priority": 1,
              "dueDate": "2026-04-11T00:00:00Z",
              "assigneeId": "0abb0e37-..."
            }
          }
        },
        "outputs": {
          "issue_id": "data.issueCreate.issue.id",
          "issue_identifier": "data.issueCreate.issue.identifier"
        },
        "depends_on": []
      }
    }]
  },
  "confidence": 0.97,
  "extraction_tokens": 0,
  "generated_at": "2026-04-04T00:00:00Z"
}
0
tokens to generate this plan.
The catalog does the reasoning.
0.4s
average plan generation time.
MCP takes 10–30 seconds.
97%
confidence. Every field resolved.
No silent assumptions.
THE PROBLEM

Every action-oriented request costs your agent time, tokens, and reliability.

🔥

Token burn

Every action-oriented request forces your LLM to reason through APIs, guess at field shapes, and figure out sequence. That reasoning costs tokens every single time.

⚠️

Silent assumptions

MCP servers auto-create entities, guess at values, and make decisions without asking. The 10,000th 'create urgent bug' makes the same mistakes as the first.

🔧

Integration debt

Every new software tool is an engineering project. Build an MCP server. Define tools. Handle edge cases. Maintain it forever. Multiply by every provider you need.

HOW IT WORKS

Three steps. Zero reasoning required.

Agent intent

"create urgent bug assign to me"

POST /plan

Unaka

Execution plan

{ status: "ready", steps: [...] }

Without UnakaWith Unaka
SetupManual per toolCatalog-driven
Token costHigh (reasoning every call)Zero
Speed10–30 secondsSub-second
AccuracyProbabilisticDeterministic
Data storedVariesNothing
REAL BENCHMARK DATA

Same intent. Three approaches.
The numbers don't lie.

PromptComplexityHarnessTokensAPI CallsCostCorrect
Create urgent bug for login timeout assign to meSimpleUnaka Winner01$0.00✓
MCP23,7693$0.0713✓
High priority feature, Engineering team, due next Friday, assign to meComplexUnaka Winner02$0.00✓
MCP32,0714$0.0962✓
20/20
batch routing tests passing
on Linear and GitHub
83%
cheaper than
MCP
11×
fewer API calls
on compound workflows

Benchmarked against Claude Sonnet with Linear's official MCP server. Same intents, same model, real Linear issues created. Unaka returns a plan — execution is the caller's responsibility.

Built for the teams building what's next.

SaaS companies

Get a plan generation layer for your product without building or maintaining it. When an agent expresses intent, Unaka generates the plan. You execute it. Agents work better in your product.

Agent builders

One integration. Every provider in the catalog. Your agent expresses intent, Unaka returns a deterministic plan. No more reasoning about APIs. No more token burn on tool selection.

BUILT WITH TRUST

We never see your data.
Not even a little.

Unaka sits between your agent and your software. We generate plans. We execute nothing. We log nothing about you.

🔒

Zero data retention

Intent content and parameter values are never stored. Plan outputs are stored only to enable cross-request chaining — never what was said, only what was resolved.

📊

Aggregate metrics only

We count workflow executions and success rates. Never what was said. Never who said it.

🗃

Feature requests are anonymized

Unsupported intents are stripped of all identifying information before anything is logged.

Privacy policy in one sentence: "We log that something happened, never what it was."

The planning layer is ready.

Unaka is in early access. We're working directly with SaaS companies and agent builders to expand provider coverage.

Every /plan/result callback improves plan accuracy. The catalog self-corrects from real usage.