Skip to Content
CoursesAI-Powered GTMThe AI toolkit

The AI Toolkit in Sync GTM

Outcome: each AI step in your own workflow assigned to one of five tool types, with the cheaper non-AI alternative named next to it.

Surface
App and MCP server
Level
Intermediate
Uses
AI agent columns · MCP server
Credits
0 — this lesson is a map
Prerequisite
Lesson 01

Five tools, five jobs

ToolJobCost per rowCheaper alternative
Research agentAnswer an open question by reading sources~1–2 creditsA scrape, if you know the URL
ClassifierPut a row into one of a fixed set of buckets~0.5 creditA keyword rule, for the predictable 80%
ScorerProduce a number from evidence~0.5 credit, often freeA formula — usually the right answer
WriterGenerate copy from row data~1 creditA template, if the row has no distinguishing evidence
MCP chainAssemble many tools in one passCost of the tools it callsA table, when the run repeats weekly

Lesson 01 gave you the test. This lesson is the map you apply it against.


Research agent

Use when the answer requires reading and judging. “Do they sell to enterprise?” “What does their pricing model imply about their buyer?”

Do not use it for facts a database holds — headcount, funding, tech stack, emails. It is slower, costlier and less accurate than the enrichment that exists for exactly that.

Full treatment: Research & Web Scraping lessons 05–07. Reference: AI agents.


Classifier

Use to collapse free text into a value you can filter on: a job title into a function, a description into a segment, a research answer into a bucket.

Rules first

A keyword formula handles most rows for free and is instantly debuggable. “VP Engineering”, “CTO”, “Head of Platform” → engineering.

AI on the remainder

Run the model only where the rule returned unclassified, constrained to the same closed value set.

Never let the value set drift

Written down, closed, with Unknown and at most one Other.

This split is the single largest AI cost saving available in a normal table, because classification is the most-run AI column and rules cover most of it.


Scorer

Use AI here rarely. A score is arithmetic over columns you already have, and a formula does it for free, deterministically, and explains itself.

The exception: scoring something genuinely qualitative that has no column — “how closely does this company’s stated problem match what we solve?” Even then, have the model return one of five levels rather than a number out of 100. A model’s 73 is not meaningfully different from its 68, and treating it as though it were produces a gate nobody trusts.

Lesson 12 builds the scorer properly.


Writer

Use for the one sentence that must differ per row. Not for the pitch, not for the CTA, not for the subject line — those are written once by a human and reused, because they should be the same for everyone.

The writer’s constraint set is the whole craft: one sentence, banned phrases, must reference the evidence, abstain when there is none. Lesson 14 covers it, and SyncGTM 101 lesson 15 has the base version.


MCP chain

The other surface entirely. Instead of columns running down a table, tools run in sequence inside a conversation — search, filter, enrich, verify, push, in one pass.

Use a table whenUse an MCP chain when
The run repeats on a scheduleIt is ad hoc or exploratory
Volume is hundreds or thousandsVolume is tens
Several people need to see the resultYou need the answer now
Each step needs inspectingYou trust the chain end to end

Lesson 04 is the mental model; the MCP prompting guide has the phrasing rules.

The two surfaces are not competitors. The common pattern is to prototype a workflow as an MCP chain — fast, cheap, no setup — and move it into a table once it is worth running every week.


Do this now

  1. List every step in your workflow where a model runs, or where you are considering one.
  2. Assign each to one of the five tool types.
  3. Next to each, write the cheaper non-AI alternative — a filter, a formula, a database enrichment, a scrape.
  4. Delete any AI step whose alternative would work. Most tables have at least one.
  5. For anything left, note whether it belongs in a table or an MCP chain using the comparison above.

Check your work

  • Every AI step has a type and a named alternative
  • No AI step is doing something a database enrichment does
  • Your scorer is a formula unless you can justify otherwise
  • Classification runs rules first, AI second

Where this breaks

Using a research agent to fetch a fact a database already holds is the most common and most expensive misuse in this course. It costs several times more per row, it is less accurate, and it fails silently — the model returns a plausible headcount rather than saying it does not know. Before adding any research column, check the enrichment catalogue for a tool that answers it directly.


Further automation

Once each step is typed, the cost model from lesson 03 falls out of it: rows entering each type, multiplied by cost per type. That number is what tells you whether the workflow scales, and it is much easier to compute once the steps are labelled.


Next lesson

03 — Credit discipline, the ordering rules that keep an AI-heavy workflow affordable.

Reference for this lesson: AI agents, Actions, MCP tools, AI integrations.