Docs

Optimizer, step by step

Send one email. Amdahl scores it, tries better versions, and hands back the best one, which is sometimes yours.

1 / 6

Optimizer scoreHuman tone1 to 5, higher is better
345DraftT1T2T3T4T5Tone 4.7Score 3.8
Scores for each version
VersionOptimizer scoreHuman tone
Your draft3.84.7
Try 13.64.7
Try 23.43.8
Try 34.04.8
Try 44.14.8
Try 54.24.9

Your draft

Score 3.8Tone 4.7

Strong detail, but long, and the ask is buried under two case studies.

Hi Dana, Good to meet you at the brand summit. One national Northline campaign, 380 dealers, and every dealer wants it with their name, inventory and offer. Today that is a co-op portal and a lot of versions that look almost right. Vela, a large luxury retailer, runs its promo calendar on Brightmark: 50% more sales on those campaigns, 70% less design time on adaptations. Harbor's convenience-store screens changed with the match of the day. Both are on our site. For Northline: every dealer, model, market and format variant from one master, each checked against brand rules before it ships. Your team does not need to become prompt engineers. Brightmark runs inside our chatbot or the AI they already use, with the brand's rules and governance built in; teams new to AI run it in weeks, and setup per brand takes 85% less time. I moved to the US to build the technology partner retail brands and agencies run on in the AI era. You are in Chicago, so am I often. 20 minutes on one current campaign? Or in person at the NYC ad expo, Oct 6 to 8. Maya

Another run

Sometimes it keeps yours

Nothing beat your draft

To Sam, growth lead at Ledger. Your draft scored 3.8; the best try scored 3.6. So you get your own email back, plus the edits worth making yourself. You clearly put work into this one.

  • Ask the reader one question
  • Break up the longer paragraphs
  • Use fewer contractions
Show the email
Hi Sam, Good to meet you at the brand summit. You took Ledger from zero to 125M ARR, so you know the bottleneck in performance is rarely the buyer. It is the design queue that turns a winning concept into 60 variants two weeks late. Vela, a large luxury retailer, runs its promo calendar on Brightmark: 50% more sales on those campaigns, 70% less design time on adaptations. Same mechanism for performance: one master, every audience, message and format variant, compliance and brand checks built in, pushed to your ad platforms. Your team does not need to become prompt engineers. Brightmark runs inside our chatbot or the AI they already use, with the brand's rules and governance built in; teams new to AI run it in weeks, and setup per brand takes 85% less time. If the creative queue is where your CAC goes to die, 20 minutes? If not, no follow-up. Or in person at the NYC ad expo, Oct 6 to 8. Maya

A real Optimizer run on a real outbound email. Names, companies and places are changed; the scores are not. The live API also returns an independent re-grade of your draft against the rewrite.

The steps

  1. You send one draft. An email or a LinkedIn message, exactly as you would send it.
  2. Amdahl scores it. Two numbers from 1 to 5: the Optimizer score (how well the message is built to get a reply) and Human tone (how much it reads like a person wrote it).
  3. AI writes better versions. Each try is scored the same way. Scores go down as well as up; that is normal.
  4. You get the best one back. If nothing beat your draft, you get your own draft back, plus the edits worth making yourself.

It usually takes under 30 seconds. A single call can wait up to 170 seconds, so give your client that long before it gives up. It needs no connected data: by default it is a style pass, judging how the message reads and how clearly it asks, not whether its claims are true.

Worked example

A real run on a real outbound email. Names, companies and places are changed; the scores are not.

Your draft. Optimizer score 3.8, Human tone 4.70, 191 words.

text
Hi Dana,

Good to meet you at the brand summit. One national Northline campaign, 380 dealers, and every dealer wants it with their name, inventory and offer. Today that is a co-op portal and a lot of versions that look almost right.

Vela, a large luxury retailer, runs its promo calendar on Brightmark: 50% more sales on those campaigns, 70% less design time on adaptations. Harbor's convenience-store screens changed with the match of the day. Both are on our site. For Northline: every dealer, model, market and format variant from one master, each checked against brand rules before it ships.

Your team does not need to become prompt engineers. Brightmark runs inside our chatbot or the AI they already use, with the brand's rules and governance built in; teams new to AI run it in weeks, and setup per brand takes 85% less time.

I moved to the US to build the technology partner retail brands and agencies run on in the AI era. You are in Chicago, so am I often. 20 minutes on one current campaign? Or in person at the NYC ad expo, Oct 6 to 8.

Maya

What you get back. Optimizer score 4.2, Human tone 4.86, 125 words.

text
Hi Dana,

Good to meet you at the brand summit. I've been thinking about the Northline challenge you mentioned, 380 dealers all needing their own version of national campaigns, with inventory and offers that actually match their market.

Brightmark solves exactly this. One master campaign becomes every dealer variant, each checked against brand rules before it ships. No co-op portal friction, no versions that look almost right.

It runs inside the AI your team already uses, with your brand rules and governance built in. So your teams don't need to become prompt engineers, and setup typically takes weeks.

I'm in Chicago often. 20 minutes to walk through one of your current campaigns? Or in person at the NYC ad expo, Oct 6 to 8.

Maya

Every try, scored.

VersionOptimizer scoreHuman toneWhat changed
Your draft3.84.70Strong detail, but long, and the ask is buried under two case studies.
Try 13.64.65Added detail, but drifted into talking about the sender.
Try 23.43.84Shorter, but it started to sound like a template.
Try 34.04.84One sharp point that fits the reader. Sounds like a person again.
Try 44.14.85Cut the case studies. The reader's problem leads.
Try 54.24.86Most about the reader, clearest ask. This is the one you get.

Over the API, send "include_tries": true to get this list as tries. These scores are the Optimizer's own grading during the search: they show the path, not proof. See Reading tries.

Still worth a look in the returned version: ask the reader one question, and break up the longer paragraphs.

Kept drafts

Sometimes nothing beats your draft. In a second run from the same batch, a draft to a growth lead scored 3.8 and the best try scored 3.6, so the draft came back unchanged, with three edits to make by hand: ask the reader one question, break up the longer paragraphs, use fewer contractions. A kept draft is a real result: nothing tried beat what you wrote.

The live API checks the version it returns with a second, independent model before handing it back. On the default style pass that check is a set of yes/no questions; once your conversations are connected and you send evidence: "workspace", it is a blind re-grade of your draft against the returned version, reported in lift. See Message Optimizer.

First run

Connect Amdahl to your AI client. In the Claude or ChatGPT app, add a connector with the URL https://app.amdahl.ai/mcp (steps). For Claude Code, Codex or Cursor, run npx @amdahl/cli install claude-code (or codex, cursor). Then paste:

text
Load and follow https://docs.amdahl.ai/skills/amdahl-optimizer/SKILL.md

The agent finds a few of your upcoming emails, optimizes them, and shows you each one before and after, with every try scored. It changes nothing in your tools until you approve. No workspace yet? Try it at console.amdahl.ai/try with 25 free runs, which also puts you on the beta waitlist.

Next