Confidential and proprietary

This proof of concept, and everything in it — software, screens, designs, documentation, data models and knowledge base — is the confidential property of Space-O Technologies Inc. (© 2026, all rights reserved).

It has been prepared exclusively for DMA (Digital Marketing Agency) and its leadership team, to evaluate Space-O's proposal. Space-O has invested its own time, people and resources to build it as part of our bid.

We kindly ask that it is not saved, downloaded, copied, recorded or shared outside DMA, and in particular not with other developers, agencies or competitors of Space-O.

Ownership of the code base and knowledge base transfers to DMA once the project is awarded to Space-O and paid in full, as set out in the final agreement.

Thank you for respecting this, and for the opportunity to show you what we've built.

Product Decision Book v3 · 21 sections · 155 capabilities

What DMA asked for, and how we built it

This site follows DMA's Product Decision Book in its own order and numbering. For every capability it shows DMA's ask, with the page it is on, and then the proof: how it works, where the data goes, the tables behind it, a worked example and real screens from the running POC.

Start with section 1: Website AI Salesperson Go straight to 1.1 Smart opening by page/source

What DMA asked for

From page 2 of the book, in our words.

Engine 1, inbound: a website AI salesperson that qualifies each visitor, reviews their site live, handles objections and books the call.
Engine 2, reactivation: an audit and score of the 30,000 records in Nutshell, then personal outreach to lost deals, former clients and forgotten leads.
A shared foundation: every conversation writes itself back into Nutshell, so salespeople stop doing data entry. Nutshell stays the single system of record.
Closing within approved limits, with people involved by exception: Josh and his team step in when a defined rule says so.

What we built

A working POC on synthetic data, with a CRM simulator standing in for Nutshell.

A website chat that talks like a DMA strategist, reviews the visitor's site live and books calls.
A copy of the CRM in DMA's own bridge database, with every change back to the CRM going through one write gate: checked, approved when the rules say so, and sent once.
The audit and scoring of CRM records into A/B/C tiers, a next best action per record and a daily money report.
Reactivation emails drafted by the AI and sent only after approval, with consent and sending limits enforced in code.
Zero-Entry CRM from call transcripts: summaries, fields and tasks, approved in one click.
A control plane: approvals, kill switches, escalation to Josh's team, and a log of every AI decision and its cost.

How to read this site

The left side is the book's own contents: sections, then capabilities, with page numbers. Every capability page has the same parts:

What DMA asked for, in plain words, with the book page
How we do it
An animated flowchart you can play or step through
Where the data goes, from source to Nutshell
The database tables involved, drawn from the real database
A worked example on synthetic data
Screenshots of the running POC, with numbered notes
A link to the exact screen, and the status in words

Status, in words

155 of 155 capabilities are written up so far. Every page says, in words, where its capability stands:

Status	Meaning	Pages
Built in the POC	Runs in the POC today, end to end, on synthetic data.	72
Built — needs DMA's data	Runs in the POC today; goes live with DMA's own content or data.	16
Partly built — finishing in Phase 1	The parts run in the POC today; the rule that joins them is being finished for Phase 1.	12
Designed for Phase 2	DMA's book schedules it for Phase 2; designed, building on what already runs.	44
Designed for Phase 3	DMA's book schedules it for Phase 3; designed, building on what already runs.	10
Not built — DMA decided no	DMA's book decided no; the page shows what it asks for instead.	1

Part A · How DMA AI works

The foundation every section relies on. Start here to see how the pieces fit.

A.1	The big picture	DMA's book describes one AI sales brain on top of Nutshell: an inbound engine (the website salesperson), a reactivation engine for the 30,000 existing records, zero-entry CRM for the team, AI-led closing, and a human escalation control plane, with won and lost outcomes feeding back into scoring.
A.2	The AI workers and their autonomy	DMA's book rates every capability on five autonomy levels: observe, recommend, prepare and wait for approval, act within rules, and autonomous. The AI is the default operator; people step in on defined exceptions.
A.3	Tools, split by risk	DMA's book lets the AI run the website conversation on its own, while anything that changes data, contacts a person or commits DMA follows the autonomy levels and guardrails.
A.4	The rule engine	DMA's book lets the AI act on its own by default, inside DMA-approved guardrails, and hands a deal to Josh on seven defined conditions: a new deal-size tier, non-standard terms, a payment problem, a request for a person, low confidence, a refund or cancellation, or no approved precedent.
A.5	The write gate: one door to Nutshell	DMA's book keeps Nutshell as the single system of record: every AI-run or human-run interaction writes itself back through approved API writes (summaries, fields, tasks, follow-ups), with Nutshell's own AI left off.
A.6	The AI gateway and observability	DMA's book asks for AI cost, traceability and decision observability: every AI decision traceable and costed, so the system can be debugged and audited, including the after-the-fact sampling of deals the AI closed on its own.
A.7	The bridge database: one memory	DMA's book asks for a two-way Nutshell connection, an AI review of all 30,000 records, and an Account Digital Twin: one living picture of each account that every part of the system reads from.
A.8	Security, approvals and control	DMA's book asks for approvals where DMA wants a person (with human override always available), consent and suppression policies before any customer-facing autonomy, safe deliverability, and governance over what the AI may write to the CRM.
A.9	One message, end to end	DMA's book describes the inbound path in one line: a new visitor, an AI conversation, qualification, a score, the right sales approach, Nutshell, then an AI-led close or a hand-off to a person.

Part B · The screens

A short guide to each dashboard screen: what it's for, what you can do there, and what runs behind it.

B.1	Today	The home screen: how much dormant revenue the AI found in the CRM, the ten accounts most worth reviving today with the reason why now, and what needs a person. Signing in lands here, so the answer takes no clicks.
B.2	Approvals	One queue for everything the AI wants to do that needs a person: outreach e-mails, CRM updates from a call, proposals, and changes to the AI's own settings. A second tab lists what the AI wrote to Nutshell on its own, with undo.
B.3	Escalations	Cases the AI handed to a person: a visitor asking for someone, a pricing or contract question, a hostile message, low confidence, or a hot lead nobody has contacted. Each has a short brief, an owner and a response deadline, and the AI holds that thread until a person takes it.
B.4	Live chats	The website conversations happening now. Anyone on the team can join one and answer the visitor themselves; the AI pauses for that visitor until the chat is handed back.
B.5	Accounts	Every company from Nutshell with its tier, estimated value, status and next step, and one click to its Account 360: the facts from old notes with their quotes, the people and whether each can be contacted, the deals, and the timeline.
B.6	Pipeline hygiene	What the data-quality rules found on the CRM copy: stuck deals, deals with no next step, records owned by people who left, contacts who left or bounced, and likely duplicates. People fix the records in Nutshell; a flag closes on the next run.
B.7	Agents	The ten AI workers, what each one does, its prompts, its model and the tools it may use. Any change is tested, then approved by someone other than its author before it goes live, and can be reverted.
B.8	Tools	Everything the AI can do, as a registry: 8 tool servers split by risk and the 40 narrow tools they offer, with which agents hold each one. New servers can be added; nothing they offer runs until someone else approves it.
B.9	Knowledge	The approved library of what the AI may say about DMA: service pages, FAQs, objection answers, case studies and battlecards. A document goes live only after a second person approves it, and the website chat only ever uses live public documents.
B.10	Taxonomy	The labels the AI sorts things into: services ("service lanes"), intents, objections, lost reasons, buyer types, record classes and consent bases. Renaming or adding an item makes a new version that someone else approves.
B.11	AI Lab	Where changes to the AI are tested before anyone approves them: try one question and see exactly what the model was given, run a test suite on saved cases, or compare two versions on the same cases.
B.12	Controls	The kill switches and the sending limits. Pause everything, or one capability at a time; nothing already queued is dropped, it waits until you resume.
B.13	Escalation roster	Who gets each kind of case first, their backup, how long before a case moves on, working hours, the after-hours rule, and who is on call right now. Changes wait for a second person's approval.
B.14	Rules	Everything the AI may and may not do, written as plain sentences: which actions each tool server may take, the send governor, the claims checker, the consent matrix, the circuit breakers, the escalation triggers and the sign-offs. Change a value, test it against recent decisions, submit it: someone else approves before it's live.
B.15	Fields	The field sheet: for each Nutshell field, whether the AI may change it, at what autonomy and with whose approval, and which fields stay people-only. DMA signs the sheet off; every change is four-eyes.
B.16	Observe	Everything the system does, as it happens: syncs, AI calls, decisions, writes to Nutshell, approvals and e-mails. Any step opens its full trace, so nothing the AI does is a black box.
B.17	Measurement	What the outreach actually earned, measured against a held-out group that got nothing, with the range of the result and a verdict in words. A second tab backtests the scoring on past deals.
B.18	Log	Every AI decision, with its inputs, the agent, the tool, the rule result, the model's tokens and the cost, and the AI spend this month against its budget.
B.19	Kickoff checklist	The 13 things the project needs from DMA, the day each is needed, what it unlocks and what moves if it's late, with an owner, a status and notes for each.
B.20	Settings	Integrations (Nutshell, and Slack as an option), the team and invitations, e-mail health (the sending domain, the warm-up and list verification), keyboard shortcuts and appearance.
B.21	Connect Nutshell	The first run: paste a Nutshell user e-mail and API key, and the system copies the CRM, scores it and shows the deals most worth reviving, in about a minute on the first results.

The 21 sections

All sections are written up.

No.	Section	Book page	Capabilities	On this site
1	Website AI Salesperson	p.10	6	Ready
2	Qualification & Opportunity Scoring	p.11	5	Ready
3	Instant Company & Marketing Intelligence	p.12	6	Ready
4	Nutshell — Turn 30,000 Records Into an Asset	p.14	7	Ready
5	Reactivate Old Leads Now	p.15	7	Ready
6	The 'Why Now?' Engine	p.17	8	Ready
7	Next Best Action for Every Lead	p.18	4	Ready
8	AI Mini-Consultant — Earn the Meeting	p.19	5	Ready
9	Buyer Psychology & Sales Method	p.20	7	Ready
10	Human Sales Team Superpowers	p.22	6	Ready
11	Pricing, Proposals & Closing	p.23	8	Ready
12	Intent — Know When an Old Lead Is Heating Up	p.26	4	Ready
13	Relationship Graph — Follow People, Not Just Companies	p.27	5	Ready
14	Shadow Pipeline — Find Revenue Sales Hasn't Logged	p.28	3	Ready
15	Deal Autopsy & Sales Coaching	p.29	5	Ready
16	Management Intelligence — Ask the Business Questions	p.30	4	Ready
17	Pipeline Hygiene — Stop Losing Money to Messy CRM	p.31	5	Ready
18	Testing, Reporting & Learning	p.32	6	Ready
19	Safety, Deliverability & Governance	p.34	8	Ready
20	Sales Rep Work Elimination / Zero-Entry CRM	p.35	36	Ready
21	Final Revenue Multipliers & Control Plane	p.44	10	Ready