Skip to main content
Platform / AI Agents

Agents that finish the job.

100+ tools, multi-agent delegation, self-improving memory, and human approval on every consequential write — orchestrated by a graph engine with hard cost caps and resumable runs.

100+ Tools·5 Starter Templates·Depth-2 Delegation·Approval-Gated Writes·Resumable Runs

Execution Engine

Every run takes the same governed path.

A state machine with conditional edges: agents plan before acting, call tools in parallel, and retry retrieval when confidence is low — with the budget gate in front of the first token.

Init
Load context, parse instructions
Provision
Apply complexity-aware budget tier
Cost Check
Pre-flight dollar gate
Plan
Break the job into steps
LLM ⇄ Tools
Reason, act, repeat — tools in parallel
Synthesize
Compile the answer with citations
Complete
Stream, verify, follow-ups

Tools

100+ ways to touch your stack.

Reads run freely. Writes carry risk tiers and wait for approval. Extend with custom webhooks and MCP servers.

Search & Knowledge10+

search_documents, search_web, recall_memory

Databases8+

NL-to-SQL over PostgreSQL, MySQL, ClickHouse, SQL Server

Google Workspace18

Gmail, Calendar, Drive, Docs, Sheets — sends from your account

Microsoft 36533+

OneDrive, Outlook, Teams, SharePoint, Planner

Support & ITSM25

Zendesk tickets + ServiceNow incidents, changes, CMDB

CRM15+

Salesforce SOQL, HubSpot records & notes, Zoho

Observability & Paging10

Datadog logs & monitors, Sentry issues, PagerDuty

Product Analytics14

GA4 reports, Mixpanel funnels, PostHog HogQL

Code Execution2

Sandboxed Python — no network, secret-scrubbed, approval-gated

Airtable + Notion20

Bases, pages, databases, records, comments

Custom Webhooks

User-defined endpoints with configurable auth

MCP Servers

Model Context Protocol tools, resources, and prompts

Delegation

A coworker with coworkers.

Agents hand subtasks to specialist agents on the same team — a research agent delegates SQL questions to a database analyst, support triage asks the code specialist about a stack trace. The parent stays in control and integrates the results.

  • discover_agents and delegate_to_agent — specialists resolved from the team's delegatable automations
  • Specialist budgets clamp to the parent's remaining iterations and cost; spend rolls up to the parent run
  • A specialist's approval-gated write pauses the parent — one approval, then the run resumes
  • Read-only parents can never gain write tools through a specialist
  • Depth-limited to two levels, with a per-run delegation cap
Delegation Trace / depth 1Live
ParentAccount Research · $0.41 of $2.00
discover_agents — 3 specialists on this team
delegate_to_agent → SQL Analyst: "churn by cohort, Q2"
budgets — clamped to parent's remaining
specialist write paused → parent holds one approval
Doneresult merged · $0.07 rolled up to parent

Memory

Self-improving agent memory.

Three layers work together so agents get smarter the more you use them — without operator intervention.

Layer 1

Persistent memory

Facts, preferences, insights, and procedures stored across sessions with importance scoring. Agents recall mid-execution via the recall_memory tool.

Layer 2

Observational memory

After every long turn, a lightweight model distills findings, tool usage, and pending items into a compressed summary — 80%+ token compression on 50-message conversations, cacheable so prompt caches hit.

Layer 3

Procedural memory

Successful multi-tool sessions distill into reusable playbooks. The agent recognizes similar jobs and reuses the steps that worked — admins curate, publish, and version the library.

Scope

Team-level or user-level memory isolation

Retention

Configurable TTL with automatic cleanup

Consolidation

Periodic similarity-based dedup of overlapping memories

Write hygiene

Rate limiting, deduplication, type validation

Budgets

Predictable costs. Resumable runs.

Every run is capped before the first token is spent. If a budget exhausts mid-research, the agent delivers a partial answer and a Continue button — nothing is lost, nothing re-runs from scratch.

Dynamic budget tiers

The orchestrator classifies each query and applies the right tier — upward only, so operator floors are never shrunk.

Pre-flight cost ceiling

Worst-case cost is estimated before the first LLM call; runs over the per-run cap are rejected immediately. A live meter shows spend as the run progresses, plus optional rolling 24h team caps.

Pause & resume

Exhausted budgets checkpoint the full run state for 7 days. Continue extends the budget and picks up exactly where it left off; automations auto-resume on the next tick.

TierWhen it firesIterationsTokensWall-clock
FactoidSimple lookup questions1050k2min
ProceduralHow-to / step-by-step1580k3min
ExploratoryOpen-ended research25150k5min
ComparativeN-way comparisons30180k6min
AutomationScheduled deep research50300k10min

Reliability

Built for the long tail of real work.

Every agent ships with the resilience features on by default — no flag-flipping, no extra wiring.

Approval-gated writes

Every tool carries a risk tier (T0–T5). Consequential writes pause the run and route to the right human — even when a delegated specialist is the one writing.

Auto-recovery

Transient tool failures (timeout, rate limit, 5xx) retry once before escalating to the LLM. Recovery retries don't count against the tool-call budget.

Context compaction

Long conversations are summarized in place before they crowd out working memory — token-aware, triggering at 50% of the context window.

Verification contracts

Automations can require minimum confidence, minimum sources, or a non-empty answer — agents self-evaluate before completing.

Canvas

Work products, not just answers.

Agents draft versioned artifacts — reports, code, plans, JSON — in a side panel with diff view, version history, and direct editing.

  • Markdown, Python, Go, TypeScript, JSON
  • Version history with diff comparison
  • Edit artifacts directly; the agent revises from there

Extensibility

Teach it your internal tools.

Wrap any internal endpoint as a tool, or plug in MCP servers — new tools inherit the same risk-tier and approval policies as the built-ins.

  • Custom webhook tools with configurable auth and timeouts
  • MCP servers over SSE, streamable HTTP, or stdio (self-hosted)
  • Sandboxed Python for analysis the tools don't cover

Automations

The agent, on the clock.

An automation is an agent with a job description and a trigger. The agent can even draft and manage its own — gated by approval, per team.

Triggers

Cron schedules, inbound email, webhooks from Jira / Zendesk / GitHub / Salesforce / HubSpot, and meeting events.

Verification

Acceptance criteria (min confidence, min sources), stale-state checks, and bounded auto-resume on paused runs.

Delivery

Results land via webhook, Slack channel, or email — with attribution footnotes on external writes.

Templates

5 ways to start.

Pre-built blueprints with system prompts, tool selections, and knowledge base connections. Clone and make them yours.

Support Triage Agent

Classifies tickets, searches the knowledge base, drafts responses

Sales Briefing Agent

Compiles prospect research from CRM, email, and documents

IT Helpdesk Agent

Resolves common issues, escalates complex problems

Compliance Reviewer

Checks documents against policy, flags violations

Onboarding Assistant

Guides new hires through setup, answers policy questions

Get Started

Build your
first agent.

Start from a template or from scratch — see it plan, act, and ask for approval in the live demo.