Chat With Peer
Run usage-bearing agentic search and reasoning over a peer's learned representation to answer a question. Higher reasoning levels generally cost more and take longer. Returns one non-streaming JSON response.
Honcho provides memory, context, and theory-of-mind infrastructure for building stateful AI agents.
Run usage-bearing agentic search and reasoning over a peer's learned representation to answer a question. Higher reasoning levels generally cost more and take longer. Returns one non-streaming JSON response.
Store a batch of 1-100 explicit conclusions about peers, optionally tied to sessions.
Add a batch of 1-100 attributed messages to a Honcho session. Message-level reasoning settings can trigger usage-bearing processing.
Permanently delete one known session and its session-scoped data. Honcho marks the session inactive immediately and completes deletion asynchronously.
Return one message by its exact ID within a session.
Return a peer by ID within a workspace, creating it with the supplied metadata and configuration when absent. Existing peers are returned unchanged.
Return a session by ID, or create it with initial peers, metadata, and configuration when absent. Creation may create missing peers and start usage-bearing processing when reasoning features are enabled; existing sessions remain unchanged.
Return a workspace by ID, or create it with metadata and configuration when absent. Enabling reasoning features during creation may start usage-bearing background processing.
Return a curated subset of conclusions representing a peer. Supplying search_query performs semantic retrieval and may consume paid search capacity; omit it for the existing default representation.
Return one page of stored conclusions in a workspace; use Search Conclusions for semantic retrieval.
Return one page of messages in a session; use Get Message for exact-ID retrieval.
Return one page of peers in a workspace.
Return one page of sessions in a workspace.
Return one page of Honcho workspaces visible to the connected admin key.
Semantically search stored conclusions in a workspace. This operation may consume paid search or embedding capacity; use List Conclusions to browse stored conclusions without semantic retrieval.
Semantically search messages at workspace, peer, or session scope. WARNING: this operation may consume paid search or embedding capacity; use list or get message tools for exact or chronological retrieval.
The Honcho integration connects your Dench AI CRM directly to Honcho, so agents can read and act on your Honcho data as part of everyday work — answering questions in chat, keeping your CRM in sync, and running automations without anyone copying data between tools.
16 actions are available for agents to invoke on your behalf. Every call runs through Honcho's own authorization, scoped to the account you connect.
Sign in to your Dench workspace and open Integrations.
Find Honcho and click Connect — you'll authorize access through Honcho's own sign-in flow. No API keys or code required.
Ask an agent to use Honcho in chat, or call it from an automation.
Manage or disconnect the connection any time from workspace settings.
The Dench Honcho integration connects your AI CRM to Honcho, so AI agents can work with your Honcho data as part of chats, automations, and CRM workflows. You connect your account once, and every agent in your workspace can use it — governed by your workspace permissions.
The Honcho integration currently exposes 16 actions, including Chat With Peer, Create Conclusions, Create Messages, Delete Session, Get Message, and Get or Create Peer. Agents invoke them on your behalf from chat or from automations.
No. You connect Honcho from your Dench workspace using Honcho's own sign-in and authorization flow — no API keys to copy, no glue code to maintain.
Connections are authorized through Honcho's own authentication flow, and Dench stores only the authorization needed to act on your behalf. You can review and disconnect the Honcho connection from your workspace settings at any time.