Report · Wednesday 2 September 2026

An agent owns the middle of every accelerant. It owns neither end — and that is the design, not a limitation.

Dil's question, and it is the right one: can these agents run the services we actually sell? The answer is no, and the interesting part is where each one stops. Every accelerant has the same shape — a person decides, an agent researches and drafts, something publishes, an agent measures. The agents do three of those five, in all seven accelerants. This report draws it, then walks each accelerant to the exact point where it stops and says what would close the gap.

3 of 5stages an agent can own
0 of 7accelerants it can run end to end
2different reasons it stops — and only one is fixable
0new test firms to build. We have two

The short answer No, an agent cannot run an accelerant on its own. Not because we do not trust it — because publishing needs a connected account and reaching a customer needs a person. Those are two different walls and they get confused constantly.

But it can do the slow middle of all seven, every month, per client, for pennies. That is the part that does not scale with people.

The shape every accelerant has

Newsletter, ads, microsites, the Home Pro Network — different content, identical pipeline.


PERSON AGENT AGENT ACCOUNT + PERSON AGENT Decide Research Draft Publish Measure the offer, the voice,the town the market, the client'sbrain, last month the letter, the page,the ad, the reply GoHighLevel, the site,the ad account what happened, andthe monthly report THE GATE It stops here for two different reasons ① Policy — it reaches a customer or spends money, so a person says yes. Permanent. ② No connected account — it physically cannot publish. Fixable, and it is the one that killed the sixteen. what it measured tells the person what to decide next month
The agent owns research, draft and measure in every accelerant. It never owns decide or publish. Reason ① is deliberate and stays. Reason ② is just a missing connection — and it is what made sixteen specialists useless: a channel agent without its channel is a charter, not a worker.

The two walls, and why mixing them up is expensive


Almost every argument about what an agent can do collapses once these are separated.

① Policy wall② Capability wall
What it isWe decided a person approves thisThere is nothing to publish through
ExampleAn ad that spends money. A review reply in Chad's nameNo ad account exists. No vendor list exists
Can we remove it?Not for anything that reaches a customer or the bank. That rule is the productYes — connect the account, build the list
What happens if we ignore itSomething goes out in a client's name that nobody choseThe agent flails, invents, and gives up. This is what happened to the sixteen

The test that decides whether to build an accelerant agent Not "would this be useful." It is: is there a real job waiting, and does the agent get the tools that job actually needs? An accelerant agent that would draft into a channel we have not connected fails the second half — and we already know exactly what that costs, because we archived sixteen agents in August for precisely that.

The seven, and where each one stops

Walked one at a time rather than picking the flattering ones.


AccelerantWhat an agent does aloneStops atTo close the gap
Client & Agent Newsletter Finds the content, writes both letters, writes the note on what it used Sending Ken's twelve + twelve emails first — that is the voice, and nobody else can write it. Then GoHighLevel to send. Gate ① stays
Paid Ad Management Reads the numbers, writes the report, drafts the changes, spots wasted spend Nothing to read ⚠️ Gate ② first: there is no ad account spending money. Then gate ① — a person presses the button. This is why I would not build it yet
Google Business Profile Drafts posts, drafts review replies, spots a missing or wrong listing detail Posting ⏸️ Already on hold by standing rule: no agent answers a public review in an inspector's name. Draft and surface it; a human posts. Plus per-client profile access
Local Microsites The monthly town-page refresh, as a pull request Publishing A repo token scoped to one repository, and a person merges. ⚠️ Build the sites themselves in Claude Code, free — the agent is for upkeep
Trusted Home Pro Network Writes the directory and the vendor pages, drafts the outreach Contacting a vendor ⚠️ Gate ② — the vendor list does not exist. And vendor outreach reaches a real business, so gate ① as well
Converting Website Nothing worth paying for. Measured last week: our 31-page site is ~1.27M characters, $0 extra our usual way, $40–$90 an agent's way. Build it in Claude Code
Authority Builder Could draft the press release Syndication ⚠️ Still unruled by Ken, it is one-time rather than monthly, and it cannot even be priced — the syndication quote is a known missing input

Four of the seven have a real job waiting and a way to do the middle of it today: Newsletter, Microsites, Home Pro Network writing, and Google Business Profile drafting. Two are blocked on something that is not technology — an ad account that does not exist, and a ruling that has not been made. One should never be an agent at all.

Dil's stack: can they actually do all of it?

The full list — client websites, SEO, blog posts, Google Business Profile, social via GHL, Monday.com, Telnyx, Analytics, Search Console, and a report to the client. Walked one line at a time.


Short answer: mechanically, yes to nearly all of it. Two items need a workaround, one is blocked by a rule we already have, and the genuinely hard part is not the agent at all.

First, the thing that makes handing over client credentials sane A vault credential never enters the work space. The agent sees a meaningless placeholder; Anthropic swaps in the real secret after the request has left, and only for the hosts that credential is allowed to reach.

So code running in there — including anything the agent writes itself — cannot read a client's WordPress password or copy it out. That holds even if someone plants instructions in a page the agent reads.

⚠️ One real limit: the swap covers the request's headers and body only, never the web address. Anything that puts its key in the URL cannot be vaulted.

What you asked forCan it?How, and what it needs
Read the client's website, find SEO problems ✅ Yes Fetch the pages, restricted to that client's domain. No credential needed at all
Edit an HTML site we built in Claude Code ✅ Yes The site is in a repo. A token scoped to that one repo, injected outside the work space. It edits, opens a pull request — a person merges
WordPress with an app password ✅ Yes WordPress takes the password in a header, so it vaults cleanly. ⚠️ This is the single riskiest thing on the list — see below
Write blog posts ✅ Yes The writing is the easy part. Where it lands is the decision
Post to social via GHL Social Planner ✅ Yes — best supported of the lot We already have GoHighLevel connected, and the Social Planner is one of the parts it can write to. Tokens refresh themselves
Post to Google Business Profile ⚠️ Yes, with plumbing Google logins expire and this route does not renew them on its own. Workable, but it is the fiddliest piece. ⏸️ And our own rule already says no agent posts in an inspector's name — that was written for reviews and it points the same way here
Monday.com — document the work ✅ Yes Straightforward. Key in a header, vaults cleanly
Telnyx call data ✅ Yes Same shape. ⚠️ Though we already keep the call data ourselves — worth checking we need Telnyx directly before wiring it
Google Analytics + Search Console ⚠️ Yes, with the same plumbing Google's service logins have to be signed before the request leaves, which is the one thing the vault cannot do for us. The fix is small — we mint the pass on our side and hand it over — but it is a real piece of work, not a checkbox. Read-only, so no risk once connected
Build a report from all of it ✅ Yes This is exactly what the checker already did for 54 cents
Send that report to the client ⏸️ Draft yes, send no It reaches a customer, so it waits for a person. Same rule as everything else

So what is actually hard?

Not the agent. Three other things, and the first one is the one that bites.


1

Keys. One per client, per service, times fifty.

Look at what one client needs: a WordPress password, a Google Business login, an Analytics permission, a Search Console permission, and a GoHighLevel account. That is five. At fifty clients it is two hundred and fifty — to ask for, store, keep working, and take back when someone leaves.

We already know what one bad key costs. Today a single key stopped working and it took down Parker, Josh's web chat, James and the quality reader, on our own site, and nobody noticed until we went looking. Now imagine that on a client's website.

The storage is solved. The asking, the chasing and the taking back are not, and they are people-work that grows with every client.

The real bottleneck
2

A WordPress password lets it change a live business website

Everything we have built so far could only read, or could only propose. This is the first thing that can change something a client's customers see, on a site we do not own, without anyone looking first.

That is not an argument against it. It is an argument for not starting there.

Highest risk on the list
3

Everything at the end of the chain reaches somebody

A blog post, a Google post, a social post, a report in the client's inbox — all of it is public or lands in front of a customer. That is the gate we already have, and it does not move for this.

⚠️ And do not price this off the 54 cents That figure was a read-only helper reading three files we handed it, with no internet at all. This one visits websites, calls five or six services and writes real content. It will cost several times more, and I am not going to guess how much. The same rule applies: build one, run it once, read the bill.

The better way in, and I would say this before building any of it


Draft. Do not publish. WordPress can take a post as a DRAFT. Social and Google posts can sit in GoHighLevel waiting for approval. The report can land in the client's portal instead of their inbox.

That is almost all of the value with none of the "an agent changed my website" risk — and it is the same shape as the rule we already keep for review replies.

Publishing on its own is something a client earns into later, one at a time, not where we start.

A staged way in — each step earns the next

  1. Read and report only. Website, Analytics, Search Console, call data. No password that can change anything. This alone is a monthly report no client of ours gets today, and it is the cheapest thing to build.
  2. Add drafting. Blog posts as drafts, social and Google posts queued for approval. Still nothing publishes itself.
  3. Add publishing, per client, when they ask for it — and only for the ones who would rather we just got on with it.

And measure at every step

  1. Step one, run once, on one client. Read the bill before step two.
  2. The checker proved that works. It also proved my estimates were wrong in both directions.

So what should the test account be?

Two things could be meant by that, and the answer differs. Both are short.


A

A test client to run accelerants against — do not build one. We have two.

XYZ Home Inspections (xyz) was built on 1 September for exactly this. It is the wide one — nearly the whole service catalogue, banded pricing, packages, every follow-up email on. PDF Inspection Services (pdf) is the narrow one, four services and a flat price, built so refusals can be tested.

Three reasons they beat a fresh account: they went in through the real onboarding form, not a seed, so the CRM record, the sub-account, the portal login and the welcome email all exist. They are flagged in code — isTestFirm(slug) — so the build board does not count them and the CRM note opens with a NOT A CLIENT banner. And the slugs are reserved, so a real company can never collide with one.

Use xyz for the newsletter test — it has the widest catalogue, so it is the one that exercises the most content.

Already existsZero to build
B

A separate Anthropic workspace for the agents — yes, worth doing

A workspace of its own, with its own key, is worth the five minutes:

Agent spend lands on its own line, so the cost-per-client question Beth is working on gets a clean answer instead of one tangled with the q app's usage. And a mistake in an agent cannot touch the key the live app runs on — separate keys, separate blast radius.

⚠️ One gotcha worth knowing before you make it. Session links in the Console are per workspace. If the key belongs to a workspace other than Default, the trace link our script prints will land on "Session not found" — the session is fine, the link is looking in the wrong place. Tell me the workspace ID once and I will put it in the script.

Five minutesDo this before the $5 test

What I would do, in order


Before anything is built

  1. Make the separate Anthropic workspace and put the key in it. Five minutes, and it makes every number after it clean.
  2. Run the $5 Checker test. It is not an accelerant, and that is the point — it is the cheapest way to find out what a real run costs before betting a client-facing service on an estimate.

Then the first accelerant, and only one

  1. The Newsletter, against xyz. It is the best fit, it has a test firm with the widest catalogue waiting, and the whole thing can be proven without touching a real client — draft both letters, read them, and never press send.
  2. Ken's twelve and twelve is the real blocker, and it is not engineering. An agent with no voice will invent one, and it will be nobody's.

What I would not start

  1. Paid Ads — no ad account, so there is nothing to read. It passes the day there is spend, not before.
  2. Authority Builder — unruled, one-time, and unpriceable until the syndication quote exists.
  3. Anything that publishes on its own. Not in the first version, and not without Ken ruling on it specifically.