health
Clinical context, lab interpretation, supplement stacks. Rex stays current on your panels and writes versioned updates back into your Health profile.
Boardbox is a workspace for AI: specialist agents per channel, profiles that actually know you, and memory that lasts — with standing orders to push back, not flatter.
Run me through last week.
Remission held. Patchwork shipped. Sleep didn’t.
Health: Humira injection on schedule Sunday night. No GI symptoms through Wednesday. Four lifting sessions completed — you hit 285 on deadlift, which puts you on track for 315 by your birthday. Gastro follow‑up is in 6 weeks.
Patchwork: Slack triage feature shipped Tuesday. Three new teams signed this week — MRR is now $2,040. Tunde handled the onboarding docs without intervention. Twitter thread on incident runbooks got 1,200 impressions.
Sleep: Averaged 5.4 hours, worst week since the February flare. Four of five nights under 6 hours. The pattern is identical to pre‑flare February: launch sprint → sleep collapse → symptoms appear 5‑7 days later. You know this.
Unresolved: Charleston trip with Hannah still unscheduled. You’ve opened the thread three times without committing to dates. Her grandmother is 91.
Work, health, finance, faith — generic AI may have memory now, but it still behaves like a chatbox: context is cue-dependent, stale facts leak across projects, and a new conversation can start cold. Switching topics dilutes the model.
Life orchestration · Avery
UC, fitness, sleep · Ward
Indie startup ops · Tunde
Cashflow & runway · Ledger
Theology & practice · Salt
One workspace. Five rooms. Each with its own specialist, its own memory, its own slice of you.
Forget the all‑knowing assistant. In Boardbox, every channel runs its own specialist — with its own system prompt, its own tools, and its own slice of memory. Switching topics doesn’t dilute the model. It changes the room.
Learn moreClinical context, lab interpretation, supplement stacks. Rex stays current on your panels and writes versioned updates back into your Health profile.
Cashflow, runway, tax surfaces. Knows what's a transfer vs a real expense.
Compensation strategy, resume edits, founder/IC tradeoffs. Reads tone, not just text.
Theology, scripture, prayer life. Speaks in your tradition, not a generic one.
Dating dynamics, friendship audits, hard messages drafted with care.
Macros, meal plans, grocery deltas. Will rewrite the week if labs change.
A memory dump of “I am 36, I live in Durham, I am a staff engineer” is not who you are. Profiles construct a long‑form, structured story across identity, work, relationships, health, and faith — and every channel reads only what it needs.
Learn moreCatholic. Came in through RCIA, not cradle. Prefers a homily with teeth over sentiment.
Weekly mass at St. Thomas More; confession every six weeks. Re-reading Crossing the Threshold of Hope.
Ulcerative colitis, in remission. Humira biosimilar, biweekly, self‑administered Sunday nights.
Calprotectin 48, down from 180 at diagnosis. Next colonoscopy October.
36, Durham‑based staff engineer, two kids under seven, lifts in the basement before the house wakes up. Daily rhythm built around the illness, not the ambition — gym, work, mass, repeat.
Patchwork — an incident‑response tool for small eng teams. The side project that might one day fund a four‑day week. Ships in TypeScript, ships small, ships often.
Direct, technical, no padding. If something’s not working, say so before the fourth retry.
Your health agent loads your Health profile by default. It can also pull in Financial when you’re weighing the cost of a procedure, or Spiritual when stress shows up in your sleep. Your life isn’t siloed by topic; your context shouldn’t be either.
When a thread surfaces durable context — a lab result, a salary change, a shift in conviction — the agent can commit a profile update. You get the diff, attribution, and restore path.
Every profile is plain prose, diffable, and time‑stamped. Re‑take it any time, or roll back to last month’s you.
A curated set of vertical templates ships out of the box — Personal (always loaded), Health, Faith, Fitness, OCD‑clinical. Each is a long‑form document the model treats as canon.
Boardbox keeps two indexes — one for the workspace, one per channel. Agents consult them like a librarian’s card catalog: cheap to scan, decisive about what to load, surgical about what they pull into context.
Learn moreOne source‑of‑truth listing every channel, every profile, and every artifact in your workspace — with stable IDs.
Every thread in a channel reduces to a one‑line description. The agent reads the index first, decides what’s relevant, and only then loads the thread itself.
Every image, PDF, and document lives in a workspace‑wide media library. Agents decide on their own when a file is relevant and load it — no copy‑paste, no re‑uploading, no “as I mentioned before”.
Learn moreYou haven’t talked about your labs in a month. You ask Rex about a new symptom. He doesn’t ask for the file. He decides it’s relevant, loads it, and answers grounded in what’s actually in your panel.
Channels keep the topic. Threads keep the question. A model that lives inside a 200‑message ChatGPT history goes blurry. A model living inside a sharp, scoped thread stays sharp.
Learn moreResolve a thread when you’re done. The agent stops re‑reading it on every turn — but the index still remembers it for next time.
Deep Agents are long-running, steerable runs inside your workspace. They read the context Boardbox already has, use tools, delegate to specialist subagents, update artifacts, and leave a versioned trail.
Give Boardbox a goal, not just a prompt. The run has status, budget, tool calls, artifacts, and continuation state.
Deep Agents can delegate focused review to CEO, CPO, engineering, growth, marketing, and finance lenses.
Pause when judgment is needed, correct direction, then continue the same run instead of starting a new chat.
running · 4 tools · 5 subagents
Audit the launch plan and produce the strongest next sprint.
Loads product strategy, open threads, user profile, and relevant artifacts.
CPO, engineering, growth, marketing, and finance pressure-test the plan.
Updates the sprint artifact and leaves a versioned trail.
Internal profile and artifact updates are versioned. External writes stay approval-gated.
Most AI sits and waits for you to type. Boardbox Agents wake on a cron, read what they need, do the job, and post the result. The work happens while you sleep — the morning report is already there before you open the app.
Mon–Fri at 08:00 in your timezone, every Friday at 16:00, the 1st of the month — whatever the job actually needs. Same expressiveness your servers run on.
Each run writes a new version of the agent's target document — diffable, time-stamped, rollback-able. The artifact's history IS the agent's memory of prior runs.
A scheduled agent can update artifacts and profiles automatically, but every change lands with diff history, attribution, and restore. External writes still require the right approval gate.
Start from a blank brief, pick a template, or hit "Make recurring" at the bottom of any thread to turn the work you just did into a job that repeats.
Weekdays · 08:00 · America/New_York0 8 * * 1-5
→Q1 ad performance · v23
Mondays · 09:00 · America/New_York0 9 * * 1
→Investor brief · v6
Every day · 07:30 · America/New_York30 7 * * *
→Posts in #health (Conversation mode)
Weekdays · 09:00 · America/New_York0 9 * * 1-5
→TSLA daily brief · v118
Fridays · 16:00 · America/New_York0 16 * * 5
→Sprint review · v4
Every run posts an announcement to its home channel and writes a new artifact version. Three consecutive failures auto-pause the agent.
A workspace is the unit of memory. Personal workspaces are wired around your life — multiple intimate profiles, no one else in the room. Professional workspaces flip the model: shared agents, team‑level context, role‑aware permissions. Nothing leaks between them.
Learn moreAn honest second brain. The profiles know you, the agents are yours alone, and nothing leaves the workspace.
A team workspace, but the participants are agents. Standups, postmortems, design reviews, customer summaries — all with continuity.
Boardbox agents don’t just talk — they connect to the tools you already use. Pull revenue from Stripe, tickets from Linear, docs from Notion, and events from Google Calendar. Every tool call is logged, every data load is traceable.
Learn moreIssues, projects, and sprint workflows
Repositories, PRs, issues, and CI/CD
Documents, databases, and wikis
Messages, channels, and workspace data
Payments, subscriptions, and revenue
Product analytics and feature flags
Files, documents, and spreadsheets
Events, scheduling, and availability
Error tracking and performance monitoring
User analytics, funnels, and retention
Ad campaigns, performance, and spend
Campaigns, keywords, and reporting
Subscriptions and subscriber analytics
Design files, components, and comments
Customer conversations and support data
More integrations shipping every week. Request yours at hello@tryboardbox.com
Pricing
Personal is $20/mo. Pro is $100/mo. Max is $200/mo. Personal is chat with persistent memory; Pro and Max add agents, integrations, and Opus. Annual gets you two months free on any plan.
See full pricing breakdownPersonal
Your AI, with memory and a spine — for one life.
or $200/yr ($16.67/mo — 2 months free)
Pro
Managed AI included for regular Boardbox usage.
or $1000/yr ($83.33/mo — 2 months free)
Max
More managed token budget for heavier usage.
or $2000/yr ($166.67/mo — 2 months free)
Top-ups never expire
Your monthly budget refreshes in full each billing cycle — unused monthly budget doesn’t roll over. Top-ups are separate: they never expire and carry across cycles until you use them.
No refunds
Cancel anytime through Stripe — you keep access until the period ends. We don’t refund partial months or unused top-ups.
Switch anytime
Move between plans in the billing portal. Annual subscribers get the unused portion credited on switch.
Boardbox keeps your context, holds its ground, and produces work that lasts.
Get started →