June 2026

June kept context from resetting: Vega and Polaris held onto workspace state across turns, and Contacts and Companies picked up real dedupe and merge tools. Campaigns split off into its own module with a dedicated Playbook Crafting Studio, and the Feedback Inbox gained configurable KPIs and inline source linking. Theme of the month: Context, converted.

In this edition

From Andy

Somewhere in the second week of June I went looking for one contact and found three of them. Same person, one row from a LinkedIn import, one typed in by hand, one auto-created off the back of a feedback item. Small thing, but it's the kind of small thing that tells you a product is growing faster than its bookkeeping.

So June turned into cleanup mode in a few places at once. Contacts and Companies got a real merge workflow instead of a shrug. Campaigns split out from being a feature bolted onto Contacts into its own module, with playbooks living in their own studio instead of getting edited mid-campaign. Delivery started keeping its own paper trail with GitHub and Jira instead of leaving that syncing to whoever remembered to do it.

None of it is flashy. It's the unglamorous work of making sure the product doesn't quietly diverge from what's actually going on in a workspace.

Fewer duplicate contacts. Worth it.

— Andy

Campaigns becomes a module of its own

Campaigns used to live as a feature tucked inside Contacts, playbooks edited live in the middle of a running campaign. That's gone now. Campaigns is its own module, and Playbooks moved into a dedicated Crafting Studio for building stage sets, cadences, and operator instructions before a campaign ever launches, not while it's already running.

The module covers more ground than the name suggests. Run a Problem Interview, Solution Interview, or MVP Interview campaign to work through discovery with real people, or run an outbound campaign on LinkedIn or X to test whether a topic gets traction before you commit to it. Same pipeline, same playbook mechanics, different goal at the end of it.

The campaign pipeline itself grew up alongside the split. Stage classifications like Success and Cleaning give runs a shape, spreadsheet and Kanban views cover the two ways teams actually like to look at a pipeline, and a slide-over Member panel handles next actions, touchpoint logging, and turning a member's response straight into product feedback without leaving the panel.

Campaigns is now its own module, separate from Contacts, with dedicated navigation
Playbook Crafting Studio for building stage sets, cadences, and operator instructions independent of live campaigns
Customizable pipeline stages (e.g., Success, Cleaning) with both Spreadsheet and Kanban views
Campaign Member slide-over panel for next actions, touchpoint logging, and stage transitions
Convert a campaign member's response directly into product feedback from the Member panel
Campaign Success Metrics cards with inline sparklines and drill-down into Signals

The inbox gets teeth

The Feedback Inbox stopped being a plain list this month. KPI cards now sit at the top, Open and Closed Feedback, Open and Closed Themes, the Open/Closed Ratio, and a Severity Distribution, and you choose which ones show and in what layout. Source and people linking moved inline: connect a contact or company right from the inbox row, or from their own detail page, without opening a separate dialog.

Feedback also got heavier. Screenshots and files attach with drag-and-drop and get compressed client-side before upload, comments turned into real threaded discussions with a markdown editor that even accepts a pasted spreadsheet table, and a privacy-preserving Recent Feedback view tags items with Capability Insights so you can scan what's coming in by what part of the product it touches, without exposing raw user text.

Configurable KPI cards (Open/Closed Feedback, Open/Closed Themes, Open/Closed Ratio, Severity Distribution) with saved layout preferences
Inline source, contact, and company linking from inbox rows and detail views, with items now linkable to multiple people and companies at once
Drag-and-drop attachments for files and screenshots with client-side compression
Threaded, rich-text comments with markdown preview and table paste support, included in AI assistant context
Privacy-preserving Recent Feedback view with Capability Insights tagging and timeframe/relevance filters
Authorized MCP clients can submit feedback directly into the inbox

Records that clean themselves

Contacts and Companies picked up a real immune system this month. Creation flows check name and email against active and archived records before letting a duplicate through, inline warnings offer to restore or merge instead, and a built-in merge workflow folds relationships, accounts, campaign links, and activity into one canonical record when two turn out to be the same person or company anyway.

Search got steadier alongside the cleanup. Special characters like commas, parentheses, and backslashes no longer break a query, keyword search splits and ranks terms for better matches, and linking between feedback and contacts or companies is more reliable, every matching contact now shows up in the linking popups instead of some going missing.

Duplicate prevention on Contact and Company creation, checked against active and archived records, with a safe "Create anyway" override
Built-in merge workflow that consolidates relationships, accounts, and campaign links into one record
Archived Companies, Contacts, and Campaigns are badge-visible and restorable with one click
Contacts page KPI counters now reflect active records consistently, regardless of archive filters
Search handles special characters (commas, parentheses, backslashes) without erroring
Feedback-to-contact linking reliably surfaces every matching contact in linking popups and sidebars

The paper trail closes

Delivery started keeping its own receipts. Changes now sync automatically to linked GitHub and Jira items, pushing status, summary, and description updates outward and mapping states correctly, so a closed-but-unmerged PR shows as Cancelled instead of quietly sitting in Done. PR change cards got AI-generated summaries in place of raw commit text, plus capability suggestions you can accept, reject, or re-run.

The Capability Landscape got a matching timeline: a compact calendar view for stepping through history, an import flow that previews CSV/JSON changes before you apply them, and the ability to restore something you deleted without losing the trail that got you there. Underneath all of it, Vega and Polaris held onto workspace context across turns instead of resetting each time you switched lanes, and a new Testlab section in Workspace Settings let teams opt into or hide experimental surfaces without filing a support ticket.

Automatic Changes sync to GitHub and Jira with accurate status mapping (e.g., closed-unmerged PRs show as Cancelled)
AI-generated PR summaries and capability suggestions, with manual re-run or reject controls
Compact, calendar-driven Capability Landscape timeline with historical snapshots, including soft-deleted items
Capability import/restore for CSV and JSON with change previews and rollback on failure
Vega and Polaris retain lane-specific workspace context across turns instead of resetting
New Testlab section in Workspace Settings, plus clearer consent and Agent Connection states when context can't be detected

Outcomet opens a door for outside agents

June was also the month a second product got born alongside the main one. A new service, outcomet-mcp, went from an empty scaffold to a production endpoint at mcp.outcomet.app in about three weeks. It's a remote MCP (Model Context Protocol) server, the same open standard Claude Code, Antigravity, and a growing list of other agent tools speak natively. Point one of those clients at the endpoint, sign in through the same OAuth flow you'd use anywhere in Outcomet, and it can read and act on your workspace with the same permissions a person would have.

The tool surface stays deliberately narrow for now. A connected agent can search and fetch Feedback and Capabilities, and, where a workspace opts in, read Contacts, Campaigns, and Playbooks too. The one write path so far is the direct line into the Feedback Inbox from the section above, an agent can file a piece of feedback, but nothing broader than that. Every request runs through Supabase-backed auth verification before it touches anything, and every auth, access, and write gets logged to an audit trail, so "safe by default" isn't just a design note, it's what's actually shipped.

New outcomet-mcp service, live at mcp.outcomet.app, built from scratch this month
OAuth authorization-code + PKCE sign-in, so a connected agent inherits the same identity and permissions as the workspace it connects to
Safe-read tools for Feedback and Capabilities, with optional Contacts, Campaigns, and Playbooks reads behind workspace-level flags
The first direct write tool, add_feedback, lets an authorized agent file feedback straight into the inbox under a scoped feedback:create permission
Every auth, access, and action event is recorded to an audit trail
Setup support for Claude Code, Antigravity, and other IDE/agent clients, including Windows stdio proxy handling and a browser-based demo for testing the flow locally

By the numbers

4 release weeks
23 shipping days
8 marquee modules touched: Feedback, Capabilities, Stories, Campaigns, Contacts, Delivery, Signals, Agents
1 new module: Campaigns, with its own Playbook Crafting Studio
1 new service: outcomet-mcp, a remote MCP server for connecting outside agents
1 new inbound integration: MCP client feedback ingestion

Also shipped

Signal sparklines: inline trend sparklines in the Signal Catalog and a full 30-day sparkline in Signal Detail, respecting metric polarity.
KPI trend dashlets: configurable trend sparklines across Feedback, Theme, and Signal KPI cards, standardized at the workspace level.
Planning and roadmap polish: planning controls consolidated into one vertical list, clearer timeline markers, closed themes visible on the left for throughput, and a new Themes/day velocity metric.
Capability timeline editing model: today's landscape opens editable, historical snapshots from today open read-only to protect the record.
Navigation and UI stability: KPI cards and control bars stay put during resizes and when the Agent panel opens, with consistent avatars and chat bubbles across agents.
Graph canvas reliability: Strategy, Signals, Discovery, and Feedback graphs auto-center and auto-fit more reliably, with lazy loading for long Kanban columns and lists.
Stories intake: a Content Sources tab, a drag-and-drop Kanban triage board (Inbox/Kept/Dropped), and a persistent Quick Capture modal for faster inbound sorting.

Looking ahead

June made Contacts, Campaigns, and Delivery tend to themselves more than they used to, and opened a standing door for outside agents to reach in through MCP. July likely leans further into all of it: expect the GitHub/Jira sync to reach deeper into Delivery, Campaigns picking up more of the orchestration work Playbooks started this month, and the MCP tool surface growing past its current safe-read and single-write footprint.

If you want a walkthrough of the new Campaigns module, the Contacts merge workflow, or connecting an agent through MCP, reply here and I'll set up a quick demo.