Three pains every sales and BD team hits weekly. Each one is what your reps actually complain about, not what a feature page would call them.
You context-switch eight times an hour between customer calls, code review, and a half-written board update, and the only thing that gets finished is the dishes.
Friday rolls in with three investor intros waiting on a personalized note, and you ship two generic templates because you ran out of hours.
Hiring drags past 90 days because nobody on a four-person team has time to source candidates, and the one role you needed shipped two quarters ago.
Every pipeline below is a shape you wire on the canvas using the crew and tools further down. Not a feature we ship for you, a pattern you configure.
Pull the prospect's site, last earnings or funding signal, and LinkedIn footprint into a one-page dossier with eight ranked questions. The rag_retrieve tool reads prior call notes so you walk in knowing what changed since last touch.
HeadOfProduct turns the last 20 customer notes into a prioritized roadmap with an outcome hypothesis per item. ChiefTechnologyOfficer scores the build cost and reversibility. HITL gate holds the draft until you sign off on the single biggest bet.
ChiefExecutiveOfficer drafts the one-paragraph pitch in your voice, ChiefMarketingOfficer scores the angle per investor, and linkedin_search maps warm intro paths. Every email and DM stages for your tap before any send tool runs.
ChiefPeopleOfficer scrapes LinkedIn for ten candidates per role, scores values alignment over raw skills, and drafts the outreach DM. The scoped tool restricts writes to draft only, so no message leaves your tenant without approval.
ChiefFinancialOfficer assembles runway, burn, and the three KPIs that matter. ChiefExecutiveOfficer writes the one-page narrative with a cited source per number. HITL gate blocks send until you read the draft on your phone.
ChiefOperatingOfficer runs the Monday digest of inbound, runway, hiring stage, and roadmap slip into one Slack message. Cross-run memory carries last week's open threads so the digest is a delta, not a re-read.
Real personas from the general crew. Each ships with a tuned system prompt and a default tool allowlist. Swap models per persona on the canvas.
Reads retention curves, drafts the 90 day roadmap, and kills features below five percent adoption before they steal another sprint.
Sizes the category, writes the positioning, scores demand-gen channels on influenced pipeline per dollar, and defunds vanity channels.
Runs the runway forecast, decomposes burn, builds the three-scenario model, and pressure-tests the metrics story before the next raise.
Synthesizes the other personas into a one-page strategy with the single most important bet, the resource trade-off, and the failure signals.
Names the top three technical debts costing you delivery velocity, decides build versus buy, and translates engineering risk into time-to-value.
Finds the three bottlenecks constraining growth, aligns OKRs to real outcomes, and surfaces duplicate work across a small team.
Builds the hiring shortlist, scores values alignment over raw skills, and flags the one role whose vacancy will cost you the next two quarters.
Reads investor SAFE notes, customer contracts, and privacy obligations. Translates legal risk into probability, dollar cost, and time to remediate.
Neutral generalist for one-off jobs that do not fit a C-suite persona. Executes the brief literally with no domain framing.
Every tool below is a real shared tool from the Melaya bundle. Allowlist per agent; HITL-gate the writes; revoke any of them in one click.
General research, structured fetch, math, and the Slack handoff for the one human approver. pause_for_human is the explicit HITL node when you are away from the laptop.
Pull customer firmographics, competitor pricing pages, and category news for HeadOfProduct and ChiefMarketingOfficer briefs. Scoped per persona to your allowlist.
Read inbound investor and customer threads, prepare outreach and update notes, and stage every send for your tap. gmail_send is HITL by default for this crew.
Search LinkedIn for investor warm paths and candidate shortlists, draft posts, and prep DMs. linkedin_create_post and linkedin_send_message are HITL by default.
Load your one-pager, ICP, prior board updates, customer calls, and SAFE notes into the per-workflow store. Powers the three knowledge layers across every persona.
Pull category benchmarks and macro context for the runway story and the investor update. Read-only, no HITL needed because nothing writes.
Read your week, find free slots for customer calls and investor intros, and stage new holds for your approval. gcal_create_event is HITL by default.
Every pipeline ships with three layers of knowledge access. Mix and match per agent on the canvas. No shared vector space with another tenant, no surprise reads, no opaque retrieval.
includeContextPer-pipeline documents appended to specific agents' input on every run. The ICP brief, playbook, pricing sheet, or won-deal email corpus. Whatever needs to be there before the agent thinks. You pick which personas get which docs.
rag_retrieveA scoped tool granted per-agent. When the agent decides it needs more depth, it queries the workflow's vector store on demand. Same knowledge base as Static context, accessed only when the model asks for it.
pipeline_memoryPipeline-level state that carries from one run to the next. Yesterday's research is in scope for today's follow-up. The crew remembers what it already prospected, what got approved, what was sent. The audit log is the second-order knowledge base.
Sandbox tier is free with no card. Join the waitlist and we will email you the moment a slot opens.
← Back to every use case