Maya Chen
CaptainDirect · Results-first
Maya, bottom line: the pilot cut onboarding time 40%. Two rollout options attached. Can you pick one by Friday?
Why it works: Leads with the result, offers a decision, sets a deadline. No warm-up.
Personality AI
The Crystal MCP server gives agents and assistants the missing people layer: who they are talking to, how that person communicates, and how to adapt the next message, call, or meeting to match.
The difference
Generic AI gives everyone the same answer. An agent with Crystal context delivers the same message two different ways, because the two people reading it could not be more different.
One intent
Follow up after the pilot and move toward a rollout decision.
Maya Chen
CaptainDirect · Results-first
Maya, bottom line: the pilot cut onboarding time 40%. Two rollout options attached. Can you pick one by Friday?
Why it works: Leads with the result, offers a decision, sets a deadline. No warm-up.
Sam Alvarez
SupporterSteady · Relationship-first
Hi Sam, thanks for the thoughtful questions last week. The pilot went well, and I wrote up how the rollout would work step by step, so nothing changes for your team overnight.
Why it works: Opens with the relationship, reassures about change, walks through steps.
What your agent gets
Connect once and every workflow downstream inherits the people layer. These are tools the agent calls on its own, mid-task, whenever a person enters the picture.
searchYour agent resolves a real person from an email address or LinkedIn URL while it works: no manual lookup, no copy-paste, no separate tab.
fetchEach profile carries DISC, MBTI, and Enneagram context plus concrete communication guidance: pace, detail level, what builds trust, what creates friction.
adaptThe agent rewrites the email, call script, or talk track for that specific person. Same intent, different delivery, grounded in the profile instead of a guess.
meetingsPull upcoming meetings and get group guidance built from every attendee’s personality: where styles will clash, who needs detail, who needs the bottom line.
Where it runs
Outreach, objection handling, and follow-ups tuned to how each buyer decides.
Responses that match the customer’s patience, detail tolerance, and tone.
Candidate outreach that lands on the first touch instead of the third.
Renewal and expansion conversations framed for the stakeholder reading them.
Live calls that adjust pacing and directness to the person on the line.
Recaps and next steps written the way each attendee actually reads them.
For developers
Four endpoints, bearer-token auth, typed responses. Use guidance-only mode to keep your own model in charge, or let Crystal generate the adapted output directly. The implementation guide ships with a drop-in prompt for your coding agent.
POST /v1/adapt/emailAdapt a drafted email with Crystal communication guidance.
POST /v1/adapt/promptGenerate guidance to inject into your own AI workflow. Bring your model, keep your stack.
POST /v1/adapt/call-scriptGenerate a call script adapted to the person being called.
POST /v1/prepare/meetingAttendee-level communication prep for an upcoming meeting.
Access
Personality AI is built on the same validated profiles that power the rest of Crystal. Talk to us about connecting it to your stack.
Connect Crystal to Claude, agent frameworks, and any MCP-compatible client. Profiles, guidance, and meeting prep become tools your agent calls.
REST endpoints for product and workflow teams: adapt emails, call scripts, and prompts server-side with bearer-token auth.
Crystal context inside everyday assistant conversations, no integration work required.
One connection brings personality profiles, communication guidance, and adaptive output into every workflow you run.