Brad Menezes, CEO of enterprise vibe coding startup Superblocks, believes the subsequent crop of billion-dollar startup concepts are hiding in nearly plain sight: the system prompts utilized by present unicorn AI startups.
System prompts are the prolonged prompts — over 5,000-6,000 phrases — that AI startups use to instruct the foundational fashions from firms like OpenAI or Anthropic on learn how to generate their application-level AI merchandise. They are, in Menezes view, like a grasp class in immediate engineering.
“Every single firm has a totally completely different system immediate for a similar [foundational] mannequin,” he informed TechCrunch. “They’re attempting to get the mannequin to do precisely what’s required for a selected area, particular duties.”
System prompts aren’t precisely hidden. Customers can ask many AI instruments to share theirs. But they aren’t all the time publicly accessible.
So as a part of his personal startup’s new product announcement of an enterprise coding AI agent named Clark, Superblocks provided to share a file of 19 system prompts from a few of the hottest AI coding merchandise like Windsurf, Manus, Cursor, Lovable and Bolt.
Menezes’s tweet went viral, considered by nearly 2 million together with massive names within the Valley like Sam Blond, previously of Founders Fund and Brex, and Aaron Levie, a Superblocks investor. Superblocks introduced final week that it raised a $23 million Series A, bringing its complete to $60 million for its vibe coding instruments geared to non-developers at enterprises.
So we requested Menezes to stroll us by means of learn how to research different’s system prompts to glean insights.
“I’d say the most important studying for us constructing Clark and studying by means of the system prompts is that the system immediate itself is possibly 20% of the key sauce,” Menezes defined. This immediate provides the LLM the baseline of what to do.
The different 80% is “immediate enrichment” he mentioned, which is the infrastructure a startup builds across the calls to the LLM. That half consists of directions it attaches to a consumer’s immediate, and actions taken when returning the response, resembling checking for accuracy.
Roles, context and instruments
He mentioned there are three elements of system prompts to check: function prompting, contextual prompting, and power use.
The very first thing to note is that, whereas system prompts are written in pure language, they’re exceptionally particular. “You principally have to talk as when you would to a human co-worker,” Menezes mentioned. “And the directions should be excellent.”
Role prompting helps the LLMs be constant, giving each objective and persona. For occasion, Devin’s begins with, “You are Devin, a software program engineer utilizing an actual laptop working system. You are an actual code-wiz: few programmers are as proficient as you at understanding codebases, writing useful and clear code, and iterating in your modifications till they’re appropriate.”
Contextual prompting provides the fashions the context to contemplate earlier than appearing. It ought to present guardrails that may, for example, scale back prices and guarantee readability on duties.
Cursor’s instructs, “Only name instruments when wanted, and by no means point out instrument names to the consumer — simply describe what you’re doing. … don’t present code until requested. … Read related file content material earlier than modifying and repair clear errors, however don’t guess or loop fixes greater than 3 times.”
Tool use permits agentic duties as a result of it instructs the fashions learn how to transcend simply producing textual content. Replit’s, for example, is lengthy and describes modifying and looking code, putting in languages, establishing and querying PostgreSQL databases, executing shell instructions and extra.
Studying others’ system prompts helped Menezes see what different vibe coders emphasised. Tools like Loveable, V0, and Bolt “concentrate on quick iteration,” he mentioned, whereas “Manus, Devin, OpenAI Codex, and Replit” assist customers create full-stack purposes however “the output remains to be uncooked code.”
Menezes noticed a chance to let non-programmers write apps, if his startup may deal with extra, resembling safety and entry to enterprise information sources like Salesforce.
While he’s not but operating the multi-billion startup of his goals, Superblock has landed some notable firms as prospects, it mentioned, together with Instacart and Paypaya Global.
Menezes can also be dogfooding the product internally. His software program engineers are usually not allowed to put in writing inner instruments; they’ll solely construct the product. So his enterprise of us have constructed brokers for all their wants, like one which makes use of CRM information to establish leads, one which tracks assist metrics, one other that steadiness the assignments of the human gross sales engineers.
“This is principally a method for us to construct the instruments and never purchase the instruments,” he sais.
