Melaya — Build AI agents for any job. Agentic platform for research, ops, outreach, reporting — and the only one where agents can actually trade.

// USE CASE · SALES & BD

Sales agents that prepare every move,and pause before they send.

Most outbound tools send on their own with no review step, and your reps still spend half the day in spreadsheets. Melaya lets you build a sales crew that researches the account, drafts the message, and stages every send for one-click approval. The agent handles the volume, you keep the relationship, the audit log keeps the receipts.

See the pipelines ↓
01
// What breaks today

The status quo costs more than the agent does.

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.

  1. 01

    Reps burn six hours a week on lead research and list-building before a single message goes out.

  2. 02

    Personalization at scale collapses into mail-merge tokens because the agent never reads the prospect's last earnings call, funding round, or LinkedIn post.

  3. 03

    One bad auto-send to a Tier-1 account torches a six-month relationship, and Legal hears about it before you do.

02
// Pipelines you can build

Compose. Approve. Replay.

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.

P01

Score and enrich Tier-1 accounts

Rank inbound and outbound leads against ICP, attach firmographics, funding signals, and decision-maker maps. Static context holds the ICP rules so scoring stays consistent across runs.

P02

Draft outbound sequences with approval

Generate per-prospect email and LinkedIn sequences grounded in the scored account file. HITL gate blocks send until the AE approves copy, target list, and cadence.

P03

Prep discovery calls from inbound

On inbound form submit, pull firmographics, tech stack, and prior touchpoints into a discovery brief with eight ranked questions. The rag_retrieve tool pulls past call notes so reps walk in informed.

P04

Respond to RFP sections safely

Draft technical answers to RFP and security questionnaires from approved source content. The scoped retrieval tool restricts reads to the published answer library so no unreleased claims leak.

P05

Run health checks on live accounts

Weekly red, amber, or green scoring on usage, ticket velocity, and exec engagement. Cross-run memory tracks intervention milestones so save plans do not reset each Monday.

P06

Draft partner MoUs with redline review

Score inbound partner requests on distribution, data, and credibility, then draft term sheets. PartnershipLegal flags indemnification, IP, and MiCA gaps with replay on every clause change.

03
// The crew

Sales & BizDev crew

Real personas from the sales_bizdev crew. Each ships with a tuned system prompt and a default tool allowlist. Swap models per persona on the canvas.

Prospect Intelligence

ProspectIntelligence

Researches accounts and contacts, gathers LinkedIn, event, and firmographic context, and assembles the dossier every other persona reads.

Sales Strategist

SalesStrategist

Picks the angle for each outbound move. Maps the prospect dossier to a play and the play to a message structure.

BizDev Partner

BizDevPartner

Scans for ecosystem partners, intro paths, and co-sell angles. Owns the strategic relationships, not the inbox-by-inbox grind.

Account Manager

AccountManager

Owns the existing book. Prepares QBRs, expansion conversations, and renewal nudges from the same dossier the SDR side reads.

Solutions Engineer

SolutionsEngineer

Drafts the technical answer for an active opportunity. Reads the prospect's stack from the dossier and shapes the proposal around it.

$$

Revenue Analyst

RevenueAnalyst

Compiles stage-by-stage conversion, deal velocity, forecast accuracy, CAC and LTV bands, and the bottlenecks costing the most revenue.

Partnership Legal

PartnershipLegal

Reviews MoU and partnership terms drafted by BizDevPartner, surfaces revenue-share and exclusivity risk before anything leaves the building.

Chief Revenue Synthesis

ChiefRevenueSynth

Synthesizes the rest of the crew into the one revenue narrative the CRO or board reads. Used for QBR prep and forecast review.

04
// Scoped tools

Only the actions you grant.

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.

shared/tools/scraping/

Pull firmographics, news, and event context from public pages. Scoped at the agent level so ProspectIntelligence reaches only what you allow.

scrape_pagescrape_linksscrape_structured
shared/tools/social_linkedin/

Search LinkedIn for the right people at the target account. linkedin_share is gated by HITL on every write.

linkedin_searchlinkedin_share
shared/tools/email/

Read inbound conversation history, prepare outreach, and stage every send for review. gmail_send is HITL by default for this crew.

gmail_searchgmail_sendgmail_list_threads
shared/tools/messaging/

Drop RevenueAnalyst's Monday pipeline report straight into your team channel. Same audit log as every other write.

slack_post
shared/tools/knowledge/

Build the per-workflow knowledge store from CRM exports, call notes, won-deal email corpus, and product collateral. Powers all three knowledge layers.

build_knowledge_from_textbuild_knowledge_from_file
shared/tools/core/

General-purpose research and structured fetch. The fallback when nothing more specific applies.

web_searchhttp_requestgrep_search
05
// Three knowledge layers

The crew reads what you give it.

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.

L1

Static context

includeContext

Per-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.

L2

RAG retrieval tool

rag_retrieve

A 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.

L3

Cross-run memory

pipeline_memory

Pipeline-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.

07
// FAQ

Questions we get every week.

Will agents email prospects on their own?

No, not by default. The sales crew ships with HITL on every gmail_send and linkedin_share call. The agent prepares the message; a human approves the send. You can lift the gate per-template once you trust the pipeline.

Can the agents reason over our CRM data?

Live, via scoped connector tools. HubSpot is the CRM connector (hubspot_search_contacts, hubspot_update_deal, etc), Gmail and LinkedIn read inbound threads and prospect profiles, Calendly surfaces booked discoveries. HITL gates every write. On top of those, the per-workflow knowledge store covers your ICP brief, playbook, pricing sheet, won-deal email corpus, and prior call notes through three layers: static context attaches the brief on every run, the rag_retrieve tool pulls on demand, cross-run memory means yesterday's research is in scope for today's follow-up.

Does this replace Outreach, Salesloft, or Apollo?

No, it sits next to them. Melaya is the research-and-draft layer; you keep your sequencer as the system of send. The HITL gate hands approved messages to whichever sender you already pay for, so the SDR workflow does not change.

How do we keep messages from sounding like AI?

Drafts cite specific sources from the dossier, like a LinkedIn post, a funding announcement, or your last call note, and reuse phrasings from your won-deal email corpus loaded into the knowledge store. Reps can require a citation on every draft as a HITL pre-check.

Which models can we run this crew on?

Any. Claude on the SalesStrategist where reasoning quality earns the cost, GPT on the drafting persona, a local Ollama on ProspectIntelligence when the firmographic data cannot leave your network. Each agent picks its own.

How fast can a sales team get the first pipeline running?

With Gmail and LinkedIn connectors authorized, the lead-research-to-draft workflow is a 4-node canvas: search → enrich → draft → approve. Most teams ship it in a working session and have the first reviewed drafts in their queue the same day.

How does this handle deliverability and unsubscribes?

Sends route through your existing Gmail or sequencer, so domain warmup, SPF, DKIM, and suppression lists stay where they live today. Melaya never sends from a shadow domain.

Can I audit exactly what the agent did and why?

Every run logs every step, every tool call, every model invocation, and every approval decision. Replay any run at any time. The audit log is the deal log.

Build sales & bd teams pipelines on Melaya.

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
Join the community