The wow moment · In three acts

Built. Queried. Acted on.

The same Pat at Acme, all the way through. Act 01: the profile assembles itself from a real chat. Act 02: an operator pulls it back through MCP. Act 03: the patterns surface across the tenant, and someone makes a call.

Act 01
Built from conversation
A messenger thread on the left. The Ediccio profile materializing on the right. Every record traces back to the message that produced it.
Messenger · Pat ↔ Acme
online · today, 09:14
end_user_id pat@acme.com
profile · materializing live
v.0
awaiting first signal
0.0s / 16.0s
loop
Pain
Severity, topic, description.
Lifted from a four-word sentence. No taxonomy mapping, no manual tag.
Sentiment
Polarity & arousal, not a score.
Trajectory-aware. Confidence travels with the value.
Intent
Class + skill attribution.
An opinionated schema. The agent reads it and acts.
Traditional fields
Role, company, size, country.
No form ever filled. Pulled from one sentence in line three.
Preferences
Timing & follow-up channel.
The data that turns a stalled lead into a booked call.
Conversation lands
Slack, email, support chat, sales call, anywhere your customer speaks.
Profile assembles
Five dimensions, each with the message that produced it as evidence.
Any agent can read it
Any MCP-compatible host: your own agent loop, a chat client, a scheduled job. Same record, same MCP tool.
Act 02
Queried by any agent
Rae in RevOps opens her chat client. Asks one question. The MCP tool fetches the profile from Act 01. The synthesis writes itself.
Acme RevOpsworkspace
MCP: ediccio · connectedRS
Acme · Pat
3 turns · started 14:08
RS
Rae Suresh · RevOps

What's the latest on Pat at Acme? Are they close to ready, and what should I do this week?

Ask a follow-up…
⌘ + ↵ to send
0.0s / 18.0s
loop
One prompt
No retrieval prompt, no RAG glue.
The MCP tool list lives in the chat client. Pat's record is one tool call away.
Real tool call
Visible, expandable, auditable.
Arguments in. Structured JSON out. Receipt of what the agent actually saw.
Synthesis
Talks to the operator as a peer.
Reads the record, draws the conclusion, suggests next moves. No "I'm here to help."
Citations
Every claim, traceable.
The dimensions cited link back to the records, and through them, the messages.
One profile, queried
Act 02 was a single record: Pat's.
All profiles, patterned
Now scale to the tenant: cohorts, trends, signals that say act.
Act 03
Acted on across the tenant
A commercial dashboard for RevOps, sales, and CSM leadership. KPIs that tick live, a pattern feed that earns its attention, and the same Pat surfacing in the "needs attention" list because the deadline he named in Act 01 is two days away.
Acme RevOps/Customer signals
last 7 days live · MCP
Active profiles
1244
Intent shifts · 7d
19
HIGH pain · open
14
Avg sentiment Δ · 7d
4 ·×10⁻²

Pattern feed

live · tenant-wide
  • ACTIVATION5m ago
    12 accounts have named activation pain this week, 4 at HIGH severity
    Pattern detector
  • INTENT_SHIFT11m ago
    Acme · Pat moved EXPLORING_SERVICES → EVALUATING (confidence 0.94)
    Pat @ Acme
  • SENTIMENT26m ago
    Globex · Jo trending UP across 3 contacts (Δ+0.41)
    Jo @ Globex

Sentiment · cohort

EXPLORING → EVALUATING · 28 days
Apr 22May 06May 20
+0.42polarity Δ
direction
218profiles

Intent class · distribution

active · 7 days
EXPLORING_SERVICES
412
EVALUATING
218
READY
47

Needs attention

ranked by signal recency + severity
ProfileDimensionWhat changedSignal
Sam @ Northwind
SENTIMENT−0.31 · last 3 daysyesterdayhigh
Jo @ Globex
INTENTEVALUATING → READYtodaymedium
Maya @ Initech
PAIN_POINTACTIVATION · HIGHtodayhigh
Drew @ Hooli
PREFERENCESchannel · email→slack2 days agolow
0.0s / 20.0s
loop
KPIs
Counts that mean something.
Active profiles. Intent shifts. HIGH-severity pain open. Sentiment Δ. Each one is a query against the profile graph.
Pattern feed
Signals, not notifications.
A new event lands. The detector finds the cohort it belongs to. Twelve accounts named the same pain this week.
Trajectory
Sentiment as a shape.
Not a star rating. A line, with the velocity that tells you which way the conversation is bending.
Needs attention
Profiles ranked by signal.
Pat lands here automatically. Same record as Acts 01 & 02. The deadline he named is now two days out.
Three acts, one record

Built once. Used by the agent, the operator, the team.

The same profile that powers your customer-facing AI is the one your RevOps team queries Monday morning and the one your leadership reads on the dashboard. One record, every surface, every audience. That's the wedge.

Provenance, the whole way

The evidence quote that lit up in Act 01 is what your operator cited in Act 02 and what the pattern detector grouped on in Act 03. Truth travels.

Same MCP tool, every audience

Customer-facing agent, RevOps chat, dashboard, batch job: the tool list is identical. No per-surface integration work.

One pricing meter

Active profile = a customer we touched this month. Doesn't matter whether the agent, your operator, or a scheduled job did the touching.

Try it against your own conversation.

Five design partners through July. We reply in two working days.