You connected your stack to Claude and wrote the skills. So why are your agents still guessing?
Most revenue teams stop there. FLiiP did too. What happened next follows four stages, and the last two are the hard part. This is the climb, stage by stage, and how FLiiP reached the top with Vasco.
Copy-paste your context. Memory you cannot see or control.
Access to everything, understanding of none.
Definitions the AI can read. Works, until you scale.
Systems, processes and definitions, resolved once. Where FLiiP is now, with Vasco.
Copy, paste, and hope
You copy and paste your context, your links, your documents into a chat.
A smart assistant. The latest models even keep some memory between chats.
Control. You never know what is stored, what is kept, or how well.
Then you realize two things. The AI should be connected to your tools, like your CRM. And it should be connected to your Drive and shared folders. So you connect everything.
A chatbot remembers bits of you. It does not understand your business, and you cannot see what it kept.
Connect everything. Understand nothing.
Direct access to your data and all of your company’s documentation. Now you have added so much context that it becomes unmanageable.
- Town hall deck v20
- Strategy_FINAL_v3
- SOP (2021, nobody follows)
- Strategy_FINAL_v4
- Pricing (copy)
- Town hall deck v20 (1)
- QBR template OLD
- Comp plan DRAFT
Don’t kid yourself. It is full of SOPs nobody follows anymore, anyone can edit any doc, and there are 20 versions of the town hall deck and of the strategy. How do you expect your AI to understand this mess?
Frontier models that degrade as input length grows, including on trivial retrieval tasks
Tokens now advertised per window. Anthropic's own guidance: attention is a finite budget, every token spends some of it, and returns diminish as you fill it
Best agent success on real enterprise text-to-SQL, against 91.2% on the academic benchmark
More context makes models worse, and this is measured now. The culprit is distractors: text that only looks relevant. A go-to-market stack is full of them, like four hundred rows that all look like a meeting happened.
The models solve complex math. So why do they fail when you ask if we are on track to hit the month?
Think of it in human terms
Good analysts are smart, and above all they connected the dots. They knew what each thing meant in the systems and the processes.
A good analyst also digs: the transcripts, the whole account, and the same company under a slightly different name in another system, because nothing shares a key.
- Would they get the custom formula field that calculates MRR the way your business does?
- Would they get how your sales stages work across accounts and deals?
- Would they know ACME 123 and Acme Holdings are the same customer?
Most likely not. So why expect your AI to?
Access is not understanding. Give your AI what you would give a new hire: explain the whole thing, and make it remember what means what.
A definition in a markdown file is a suggestion
I had to give my AI an easy way to understand the business. Markdown files: easy, readable by humans and AI, portable. It worked remarkably well, which surprised me. But it stopped being efficient as we scaled, for two reasons.
You are running your ETL through an LLM, every single time
Ask how many MQLs you got last week, and the agent:
- reads the CRM
- extracts the data
- reads the markdown
- writes the query
- filters
- hands you a numberon every question
Mostly right, most of the time. Slow and very expensive. Switch models and its reading of the markdown can change with it, and you would not notice.
“It was fun, but you ask the agents for a dashboard and the dashboard is not up to date. You have to ask the agent to rebuild the whole thing again. It has to redo the ETL every single time, even though I gave it the right definitions.”
Maintenance. The build ends. The operation keeps going.
AI shifted the balance between buy and build: why pay when I can build it myself? But the old costs are still there, and maintenance is the biggest one. HubSpot adds a field or someone renames the stages, and the formula breaks. It became a real problem once I took on Marketing and had to focus on more strategic work.
“Now that I am taking on marketing, I do not really have time for that maintenance any more. That is the thing, is this buy versus build?”
How to score a discovery call. What our positioning says.
My skills are markdown in GitHub, reviewed and versioned like code. I still write markdown every day.
Computed once, the same number for every agent.
A definition the model reinterprets on every question will drift.
Markdown for judgment, a metric layer for numbers. A definition the model reinterprets on every question will drift.
Getting to stage 4
One central place that makes sense of your systems and processes. It is the hard part.
- 01One central place that makes sense of your systems and processes, turns raw data into information, and uses standard definitions that fit your business.
- 02Access to that layer from the tools you already use, like Claude or your favorite AI assistant.
- 03Accepting that less context often works better.
At FLiiP, that layer is Vasco.
Vasco is the GTM brain for AI agents: the revenue context layer that lets go-to-market agents run in production.
FLiiP’s answer to stage 4 was Vasco: one context graph and metric layer, built once on top of HubSpot, so the agents read resolved answers instead of rebuilding the ETL on every question.
- 01One central place that makes sense of your systemsA context graph on top of HubSpot, with the metric layer for definitions
- 02Access from the tools you already useAvailable over MCP, where Marceau’s skills live too
- 03Less context works betterAgents get only the 6 to 20 nodes that matter
The agents, the prompts, and the skills: markdown in his GitHub repo, pushed to Vasco over MCP. Five in his first fortnight.
Extraction, identity, timelines, definitions and sync. The four jobs below, kept running as HubSpot changes.
- 4.1ExtractTranscripts reduced to typed signals, each with its evidence quote
- 4.2Resolve identityFour records become one account, reversibly
- 4.3Reconstruct Accounts TimelineEvery signal placed at the stage it was said
- 4.4Define onceOne metric, computed once, same answer every time
The transcript is mostly noise, and the noise is the expensive part
The biggest lever in the whole piece: giving the model less makes it more correct.
A one-hour discovery call is roughly 9,000 to 11,000 words. Most of it is scheduling, small talk and goodbyes. Our working estimate: about one word in ten would change a decision.
What matters in that hour: two pain points, one competitor, a champion, an economic buyer, the incumbent process, a timeline, one objection, a next step. Typed, with a link back to the sentence that produced each one, that is roughly 400 tokens.
- pain
- competitor
- champion
- economic buyer
- status quo
- requirement
- risk
- next step
About 30× fewer tokens per call in the agent's context, about 8× if every evidence quote travels with its node. And higher accuracy, because you removed distractors.
Estimate: ~10,000 words per hour at 1.3 tokens per word, one word in ten signal-bearing, ~10 nodes per call. Rounded.
Four records, one customer.
Four systems, four keys, no shared identifier. The agent sees four fragments and answers about one of them with full confidence.
- CRMACME 123
- Call recorderAcme
- BillingACME Holdings
- Slack#acme-eu
A dedup script. Fuzzy match on company name. One afternoon.
A scored match, merges you can undo, a record of why each merge was made, and the whole thing re-run every time new data lands. Forever.
An agent with unresolved identity answers about a fragment and calls it the account.
The same sentence means three different things
Take one line out of a transcript.
- CRMs+3
- Conversation+2
- Billing & Support+3
- Lead
- MQL“budget is a challenge”Qualification
- SAL
- Nego.“budget is a challenge”Deal risk
- Won
- Renewal“budget is a challenge”Churn signal
- Lead 5
- MQL 3“budget is a challenge”Qualification
- SAL 11
- Nego.“budget is a challenge”Deal risk
- Won 9
- Renewal“budget is a challenge”Churn signal
Most stacks cannot rebuild that. A CRM stores where the deal is today. It forgets when it got there and whether it moved backwards. And it matters: on Google’s Test of Time benchmark, accuracy swung from about 15% to 89% depending only on how the same dated facts were arranged. Best result: grouped by entity, sorted by time. That is an account timeline.
Then decay. A competitor mention from last Tuesday outweighs one from fourteen months ago.
Define once, compute once
You saw the problem at stage 3. The fix is a metric layer: Win rate defined once, computed once, handed to every agent as a finished number.
Pointing an agent at a raw warehouse is asking it to run the 21% task from stage 2 on your revenue numbers, from scratch, every time. The model stops deriving the number and starts receiving it.
Won deals over closed deals.
Count duplicates?
By close date or create date,
or maybe the CRM report…
- formula
- won ÷ (won + lost), by close date
- sources
- HubSpot deals · resolved accounts
- excludes
- open deals, duplicates, test deals
- group by
- segmentmotionlead sourcerep
- computed
- once, on every sync
- Claude24%
- Dashboard24%
- Yours24%
Do the hard work once, when data lands: extract, resolve, place in time, define. Then every agent reads the same truth.
What stage 4 unlocks: your AI connects the dots
Remember the analyst who connected the dots? Stage 4 gives your AI the same skill. Ask it one question and watch it walk the context graph.
- Resolved account · 4 SourcesAcme
- 21 Mar · ProposalStalled. 19 days of silence.
- 15 Mar · SlackChampion goes quiet
- 14 Mar · CallCompetitor X enters
- 14 Mar · CallBudget freeze until April
- AnswerA competitor entered and budget froze the week before.
Illustrative account.
- Root cause becomes a path6 nodes read · 0 transcripts
- Same number, every agentwin rate 24% · three times out of three
- A fraction of the tokens156,000 → under 1,000 per question
- Every answer traceableeach edge keeps its source quote
Your AI stops rereading and starts traversing. That is what makes it fast, cheap and auditable, like your best analyst.
The second question
Same number for every agent tells you the answer is consistent. It does not tell you when an agent stops deserving your trust. Everyone is racing to ship revenue agents. Almost nobody asks the two questions that matter: can we trust them, and how would we know?
What agents know: the plan, the context and the numbers, resolved once.
How agents are allowed to act: every agent runs inside it, owns an outcome, and answers for every number it acts on.
The GTM brain answers both. Autonomy is a scale: advisor, approver, supervised, autonomous. A clean record moves an agent up. A rising intervention rate moves it down.
- 1AdvisorSuggests. A human acts.
- 2ApproverDrafts the action. A human signs off.
- Illustrative agent3SupervisedActs. A human reviews after.
- 4AutonomousActs and reports.
- 1AdvisorSuggests. A human acts.
- 2ApproverDrafts the action. A human signs off.
- 3SupervisedIllustrative agentActs. A human reviews after.
- 4AutonomousActs and reports.
What stage 4 takes to build, and to keep
Not our cost. Yours, if you build it.
Gartner expects over 40% of agentic AI projects cancelled by end of 2027, on cost, unclear value and weak risk controls. Model capability is not on that list. Control is.
That split is what FLiiP did. Marceau kept building the intelligence: the agents, the prompts, the skills. The substrate he handed to Vasco, because nobody has ever been promoted for building identity resolution twice.
Buy the GTM brain, so you never rebuild the plumbing. Build what is yours on top of it.
Structure is ours, shape is yours. We hold that a definition exists and is enforced. You decide what it says.
- What it is
- The context graph: identity, timelines, signal extraction, the metric layer and sync. The same plumbing every go-to-market team needs.
- Uptime
- Around the clock. An alert fires on it.
- Who keeps it running
- Vasco, as your systems change.
- What you get back
- The team that would have maintained it.
- What it is
- Your definitions, ICP, plan, scoring, prompts, skills and agents.
- Uptime
- Changes when your business changes.
- Who keeps it running
- You. It is entirely yours.
- What you get back
- Every hour compounds.
Five questions that tell you which stage you are at
- 01Where are you on the maturity curve? Did you just plug your AI chat into all your tools and call your team AI-enabled?
If so, you are at stage 2. You gave the model more context, not more understanding.
- 02Ask two different agents for the same metric. Do you get the same number?
If not, you do not have a definition layer. You have documents.
- 03Pick one logo. Can you pull its full timeline across every system, with stage transitions, in one call?
Or does a human have to assemble it first?
- 04Take a signal from a call eight months ago. Does your system know what stage the account was in when it was said?
If not, every signal weighs the same, which means none of them mean anything.
- 05What does it cost you in tokens to answer “how is Acme doing”?
If nobody knows, that is the answer.
The models are good enough. What is missing is whether anyone made your revenue data mean something before the model read it. Answered no to two or more? The missing piece is not a better agent. It is the layer underneath it: the context your agents read, and the harness they run inside.