Changelog

• Browse and page through live CRM records and saved report results without leaving chat. Refresh a report, open a record, or drill into the data behind a result.
• Expand tables into Canvas for more room. Interactive controls retain their state, and visual choices can continue the conversation with a quick reply.
• View location cards and meeting cards with briefings that link back to their sources, keeping the supporting context close to the next action.

Learn more about working with Nash.

• Generate a social graphic as part of an Outreach draft, then refine the design before publishing.
• Keep the graphic and its post together in the drafting workflow, with accessible descriptions for the visual content.
• Connected GitHub workspaces can receive release-marketing recommendations, helping turn product changes into draft content for review.

Explore Outreach and playbooks.

• Start a deck through a conversation, using your workspace brand and a planned story to guide the slides.
• Include evidence layouts and live report blocks. Rendered design review helps catch crowded content and improve the visual result.
• Move elements with freeform dragging and grid snapping, adjust logo and image placement, and resize the properties panel while editing.

• Choose whether your workspace participates in public activity sharing from Account Settings.
• Control attribution separately from anonymous activity sharing; a workspace name is not permission to publish it.
• Keep public activity sharing separate from the work and records inside your workspace.

• Build reports from workspace data with an AI assistant and access checks that respect the viewer's permissions.
• Use interactive report controls and dashboard widgets to explore results, with richer views for research and supporting data.
• Bring live report blocks into presentations so the report can be part of the story you share.

Explore reporting.

• Ask Nash to create or manage a playbook with a goal, worker, triggers, and evidence rules. Scheduled and record-event checks decide whether there is work to do.
• Review approval requests with readable action details and links to the target records.
• Inspect task results and completion checks. GitHub release-marketing playbooks can use connected release sources to prepare content for review.

Learn how playbooks use evidence rules, including quiet runs when no action is needed.

• Build a campaign workflow with enrollment rules, ordered emails, waits, and branches. Recipients follow their own timeline, and publishing activates enrollment and delivery.
• Create emails from a creative brief, remix reusable designs with your brand, and refine generated emails in the visual editor.
• Use Campaign AI for planning and drafting, configure the sending provider, and compare delivery, opens, and clicks in campaign analytics.

See the Campaigns guide and sending checklist.

• Shared Inbox brings team assignment, internal notes, categories, rules, macros, and response targets into the mail workspace.
• Publish Knowledge articles through a review workflow, then use permitted articles to prepare replies with source references.
• Manage structured requests in Cases and invite customers to branded portals where they can read permitted Knowledge, submit cases, and reply.
• These customer-service features are available on Pro, Team, and Enterprise, with staff permissions and portal audience controls applied separately.

Start with Shared Inbox, Knowledge, Cases, or Portals.

• Configure workspace AI-provider policies to control which providers can be used for AI work.
• Optional tracking uses an opt-in consent flow.
• Regional availability checks and an interest waitlist help make supported signup availability explicit.

• Build from a prompt, import an existing page, or compose a site from reusable blocks. Generated pages can use more varied layouts, imagery, and motion.
• Browse the visual component library and manage page structure through the Sitemap and layer views, including shared headers and footers.
• Review the site brief and brand in dedicated tabs. Brand changes can be previewed before applying them to a site.

Explore Sites, page building, and publishing.

• Search across workspace content without opening each module separately.
• Open matching results directly from the search experience, with access constrained to your workspace permissions.

• Set up a workspace brand during onboarding or create one from a site brief, including logo and visual identity assets.
• Keep versioned brand kits and vector logos together, then use the brand system when generating a site.
• Preview how brand changes affect a connected site before applying them.

• Lead discovery uses your request to guide the research and the columns shown in the results, including requirements such as businesses without a website.
• Review clickable lead tables in chat and use Add to CRM to bring selected results into your workspace.
• Enrich existing records with researched facts and supporting citations, giving you sources to review before relying on the results.

Try the AI Lead Finder or ask Nash inside your workspace.

• Switch between board, calendar, map, and gallery record views, and choose the fields displayed in your record lists.
• Swipe between record details, add activity comments, and view record attachments.
• Use a unified inbox, move messages between folders, apply labels, and open received email attachments.

Learn more about Coherence for Android. iOS availability remains on the roadmap.

• Offer multiple meeting locations and collect the details you need through configurable booking questions.
• Use a static meeting URL or generate a unique Google Meet or Zoom link for a booking when the required account is connected.
• Share hosted forms with configurable branding alongside the scheduling workflow.

• Choose a primary account for exporting new contacts, while changes to existing contacts return to their original connected account.
• Enable Google write-back per source. Updates merge with the existing Google contact instead of replacing unrelated details.
• Sync maps contact data through the workspace's People fields, keeping provider data aligned with your CRM structure.

• npm install @coherenceos/sdk — the official TypeScript / JavaScript client is on npm. Fully typed, zero runtime dependencies, ESM + CommonJS, MIT licensed, Node 18+.
• Covers every /v1 endpoint: modules, records (including bulk operations), references, cross-module search, activity feeds, and agents — with agents.stream() exposing the SSE agent run as a typed for await loop.
• The SDK's operation set is contract-tested against the canonical OpenAPI spec, so the client can never silently drift from the API. See the TypeScript SDK reference.

• Every error response now includes a machine-readable code field (e.g. rate_limit_exceeded, validation_error, not_found) alongside message and statusCode. The catalog is additive-only — codes are never renamed or removed. See Errors for the full catalog.
• The live GET /v1/openapi.json endpoint now serves the complete spec covering every public endpoint, generated from a single canonical contract shared with the API implementation.
• We published our versioning & deprecation policy: breaking changes only ship under a new version prefix, and deprecated behavior gets at least 90 days notice, announced in this changelog.

• Documented endpoints, parameters, and response shapes are verified against the live /v1 implementation.
• Capabilities that are planned but not yet shipped are explicitly labeled as such instead of being documented as available.
• The published OpenAPI spec and the reference docs are kept in sync with the deployed API surface.

• POST /v1/agents/messages now streams over Server-Sent Events — opt in with an Accept: text/event-stream header or a ?stream=true query parameter, using the same request body and agents:write scope.
• The stream emits named open, token, tool_call, done, and error events so agents and UIs can render the answer token-by-token and surface tool activity instead of blocking until the run finishes. Raw model reasoning and raw tool output are never streamed, matching the privacy of the synchronous response.
• The synchronous JSON response remains the default when neither the header nor the query parameter is present; the done event carries the exact same body.

• Record listing now supports filter[field] params, a JSON advancedFilter, label and type filters, and field selection.
• New bulk endpoints: POST /v1/modules/{moduleSlug}/records/bulk create and bulk delete.
• Full module schema reads: GET /v1/modules/{moduleSlug} (fields, views, references) and GET /v1/modules/{moduleSlug}/views.
• Cross-module search via POST /v1/search, with results filtered to modules the API key's role can view.
• Read-only activity feeds: GET /v1/activity, plus per-module and per-record variants.
• Every /v1 response now carries X-RateLimit-Limit, X-RateLimit-Remaining, and X-RateLimit-Reset; 429 responses include Retry-After.

• llms.txt and llms-full.txt for LLM crawlers, plus markdown views of key pages (/index.md, and content negotiation via Accept: text/markdown).
• agents.md — an integration guide written for agents, covering authentication, the endpoint surface, and when to delegate to Nash.
• OpenAPI 3.1 spec published at getcoherence.io/openapi.json.
• .well-known/ cards: agent-card.json (A2A), agent-skills, and mcp/server-card.json.

• Run with npx @coherenceos/mcp-server and authenticate with a Coherence API key — works with Claude, Cursor, Cline, and any other MCP client.
• Read and write workspace data (modules, fields, records) through the public API.
• The chat_with_agent tool delegates multi-step tasks to Nash, the workspace agent, governed by your workspace's approval rules.

• Records CRUD on any module — list, get, create, update, and soft-delete via /v1/modules/{moduleSlug}/records.
• Module and field discovery: GET /v1/modules and GET /v1/modules/{moduleSlug}/fields.
• Scoped sk_live_ API keys with per-endpoint scope enforcement (records:read, records:write, workspace:read, and more), managed from Settings → API Keys.
• Machine-readable OpenAPI spec served at /v1/openapi.json.