System Intelligence vs. Everyone About How It Works Apply for Access →
← All Categories
Conversational AI / Operations Copilot

AskColette

“Like having a senior operations consultant on call 24/7.”
Raised
Seed
Their exact words
“Your always-on AI operations expert”
“Ask Colette anything instantly get expert answers”
“Like having a senior operations consultant on call 24/7”
The word that does the damage
Always-on.

Always-on describes availability. Not proactivity. AskColette is always available to be asked. It does not ask on your behalf. It does not act on signals. It waits. The broadcast keeps going.

What they built

A conversational AI interface with deep restaurant operations domain knowledge. The knowledge base is genuine. The answers are accurate. The experience of asking and receiving a useful, informed response is genuinely better than a manual or a search.

The gap

The broadcast is live every service. AskColette waits to be asked. At 8pm on Friday the operators who most need the intelligence are not asking. They are executing. A results engine does not wait to be invoked. AskColette does.

What They Read. What They Cannot.

THE ROOM IS BROADCASTING.
HERE IS WHAT ASKCOLETTE SEES.

What their platform reads

What you ask it. When you ask it.

What the room broadcasts that they cannot see

Everything happening in the room in real time. AskColette reads nothing proactively. No WiFi signals. No camera feeds. No device identification. No heatmaps. It responds to queries. The room broadcasts whether or not you query.

The broadcast is continuous. The questions are intermittent. At 8pm on Friday, the operator does not have time to query. The signals fire. The windows open and close. AskColette waits.

// What superGM.ai reads simultaneously
Guest WiFi traffic
What every device in the room is browsing, how long stationary, session behavior
Device signatures
Returning guest ID before they reach the host. Visit history. Behavioral profile.
WiFi heatmaps
Physical location and movement of every guest in the building. Live.
Camera intelligence
Visual behavioral signals. Table state. Crowd density. Occasion recognition.
POS + reservations
Transactions, covers, timing — fused with every other signal layer.
Voice detection
Occasion signals. Tone detection. Frustration patterns. Before the words land.
The wrapper tell
Any new hire
could build this.

Conversational AI platforms answer the questions operators remember to ask. The deeper question is what they are trained on. A model trained on restaurant domain knowledge — documentation, best practices, operational guides — knows what the industry has written down. It does not know what 600 million consumer purchasing decisions across stadiums, theme parks, and mass retail actually show about how human beings behave in rooms. That knowledge was never written down. It was observed. And it is not in any dataset a conversational AI platform can access.

You are not buying their intelligence. You are buying their access to someone else's intelligence. That access costs $20/month. They charge significantly more. The gap is a system prompt and a restaurant logo.

The consulting tell
You did not buy software.
You bought a retainer.

AskColette ships with a playbook: a guide to asking the right questions to get the right answers. The playbook exists because the right questions are not obvious. A product that requires a guide is a consulting methodology with a chat interface.

The full consulting-ware case →
Capability Scorecard

WHAT THEY CLAIMED.
WHAT THE SCORECARD SAYS.

Initiates without being asked
Responds when invoked. Never initiates.
Owns its intelligence
Frontier model plus system prompt. No proprietary corpus.
Acts on signals
Answers questions. Does not detect or act.
Proprietary intelligence corpus
Conversational AI in this category draws on frontier model capabilities rather than proprietary behavioral training data
Operates at peak service
Requires operator bandwidth to engage
No playbook required
Ships with a guide to effective questioning
// Final verdict

AskColette is a GPT-4 wrapper with a restaurant operations prompt. That is not a criticism of the product. It is a description of it. Any operator could replicate its core functionality this afternoon with a ChatGPT subscription and an hour of prompt engineering. The value they provide is the curation. The curation is a system prompt. System prompts are not a moat.

Before You Sign — or Before You Renew

QUESTIONS FOR YOUR
ASKCOLETTE ACCOUNT REP.

You positioned AskColette as an always-on AI operations expert. Before you commit, these questions are worth taking to your account representative. These are not gotcha questions. They are questions whose honest answers will tell you what you are actually buying.

Question 1
Peak service usage

“Do you have usage data from live Friday dinner services at your deployments — specifically how many queries are submitted between 7pm and 9pm? We want to understand how operators actually engage during service.”

Question 2
The data broker test

“Is the behavioral data that powers your intelligence available from any data broker? Could a competitor with sufficient funding purchase equivalent training data and build a competing model? If the answer involves restaurant transaction records, labor logs, or review scores — that data is broadly available. We want to understand what in your intelligence layer cannot be purchased or replicated.”

Question 3
Proactive initiation

“If an operator does not ask Colette a question during a service, does the platform initiate any actions or surface any alerts on its own? Or does it wait to be invoked?”

Question 4
The playbook question

“You ship a playbook for getting value from the platform. Why does the playbook need to exist? What does it enable that the platform does not do on its own?”

Question 5
Signal detection

“If a guest at Table 9 is disengaging — showing behavioral signals of a deteriorating experience — can the platform detect and surface that without the manager asking about it first?”

Question 6
On-call vs available

“You describe it as like having a consultant on call 24/7. During a live service, is the value in the platform being available, or in the platform acting? Are those the same thing for your operators?”

Question 7
What signals do you read from my room

“Walk me through exactly what data your platform reads from my dining room in real time during service. Specifically: do you read guest WiFi traffic, device identification, physical heatmaps, or camera feeds? Or does your intelligence derive primarily from POS and scheduling system integrations?”

If the answers to these questions satisfy you, AskColette may be the right platform for your operation. If the answers surface gaps you had not considered, you now have the information you need to make the right decision. Either outcome is a good one. More questions for every category →

What the category was pointing at

THE EXECUTION LAYER
function toUpperCase() { [native code] } DESCRIBED
AND COULD NOT BUILD.

AskColette — what it requires
A human who receives the alert or recommendation
A human who interprets the output
A human who decides whether to act
A human who acts — if she is available
A window that may already be closed
A CS team to explain what it all means
superGM.ai — what actually executes
Signal detected in the live stream
MERIDIAN classifies and prioritises in <100ms
GM dispatched only when judgment is required
Everything else executes without her
Window still open when she arrives
Zero consulting layer required

THE OPERATORS EVALUATING
function toUpperCase() { [native code] } RIGHT NOW
WHILE YOU READ THIS.

Every week in the evaluation is another Friday the execution layer does not run. Apply. We review individually. We move fast for operators who are ready.

The assessment on this page represents superGM.ai opinion based on publicly available information, including each company's own published marketing materials, product documentation, and publicly disclosed claims. We do not assert knowledge of any company proprietary codebase, internal contracts, or undisclosed technical architecture. Where we describe category-level architectural patterns, we describe patterns observable across the industry, not necessarily confirmed specifics of any individual product. For each company's actual capabilities, consult their own documentation.

// Other companies assessed
SignalFlare AI Nory.ai SophySays.ai Harri Black Box Intelligence Ovation MarginEdge All Categories →