CEO at Slite (YC18) | We build the first knowledge base on autopilot, in remote since 2016!

I'm the founder of Slite & Super (YCW18) 👉 Super.work 

Super.work turn all your company data into answers & AI agents for your whole team.

It comes with the recipes and tools for your team to get instant benefit from AI at work

Slite is your team dead simple yet crazy powerful knowledge base, since 2017 🔥

I'm fortunate to lead a diverse team of exceptional individuals spread across 10+ countries 🇮🇳 🇬🇷🇱🇹 🇦🇷 🇬🇧 🇳🇱 🇫🇷 🇳🇴 🇺🇸 🇪🇸 🇩🇪 🇨🇦 🇵🇹 . Our journey includes going through YC W18 batch, raising $15M+ in funding from top-tier investors like Spark Capital and Index Ventures, and serving tens of thousands of teams monthly.

Christophe Pasquier

This is my first multi-agentic workflow.
Of course, it makes the job easier but more so, it feels like the future.

Here's the setup.
I connected Claude Code to two MCPs.
1. Sanity, which is our CMS
2. Super, which holds our product knowledge, positioning, and messaging.

And here's what actually happens.
1. I ask Claude Code to QA a content page.
2. It pulls the full page from Sanity, every field, metadata, structure, all of it.
3. It calls Super as a fact-checking agent and cross-references the page against our actual product knowledge base.
4. It comes back with a plain language review of what's off, what's outdated, what's missing.
5. It pushes the approved fixes directly back to Sanity through the MCP.

The whole loop runs without me opening the CMS once.

Claude Code is an incredible general agent. 
It can orchestrate, plan, read files, execute tasks. But it's not purpose-built for anything. It doesn't know your product, your positioning, your company's source of truth.

When you pair a general orchestration agent with a purpose-built knowledge agent, the quality of output changes completely. The orchestrator handles the workflow. The specialist handles the judgment.

That's the pattern I think we'll see everywhere. Not one super-agent that does it all, but multiple agents that are good at different things, working together.

CEO Slite & Super (W18) | Most accurate search & workflows on team data

A semi-viral tweet was praising Linear's Slack agent last week
Jori Lallo quote-tweeted it with one line that's been stuck in my head since.
"Linear agent is soon just Linear."

He went on to explain that the agent will eventually have full feature parity with the UI. Everything you can do in the product, the agent can do too.

If you sit with that for a second, it reframes what a software product even is.

The UI becomes one client among many. Slack is a client. Claude Code is a client. A script someone wrote on a Sunday afternoon is a client. They all talk to the same system underneath, and they're all equally valid ways to use the product.

Most SaaS companies were built the other way around. The interface was the product, the API was an afterthought you shipped because enterprise customers kept asking. Jori is describing a world where that's completely inverted, where the system of record is the product and every interface, including the one with pixels, is just a client.

We're building toward the same thing at Slite. We shipped our MCP recently and we're still expanding it, exposing more endpoints, making more of the product fully programmable through agents. The vision is to turn Slite into a collaborative Obsidian for company knowledge, where agents search, update, reorganize, and verify docs just as naturally as a teammate would.

All SaaS products built on data as a moat are an API now, whether they like it or not.

Folks! Wanna catch up irl in Berlin next week?
I'm speaking at MCP Connect on March 3
And I'm genuinely excited for 2 reasons.

It’s college friends organising this, the founders behind Alpic, they’re moving fast on being the reference platform for anyone building MCPs and apps in the GenAI majors and it’s a blast to share stage with them. 

And ofc - Viktor Zamaruiev, Director of Engineering at Superhuman, is also speaking!

He's giving a talk on how they're thinking about AI at Superhuman. I've been a Superhuman user for years, and with their recent moves joining Grammarly and reshaping a new kind of AI productivity suite I’m extremely curious to see how they approach the connectors topic. 

I'll be talking about progressive tool calling in Super, basically what we've been figuring out at Slite and Super while building agentic RAG for company knowledge.

I'd love to see more folks who are building in this space there.
Register here: https://luma.com/olsyxsvn

Company context is the last unsolved layer in the AI stack.
The model layer is mature. Frontier reasoning is a commodity.
And that's why, today, we're announcing Super's MCP

The moment you try to deploy that reasoning inside a real company, you hit a wall that has nothing to do with model capability but everything with context.
Models need your company's entire context to do useful work.

Every team that has tried to solve this pain.
Teams have tried individual tool connections with MCP and get a fragile stack that returns incomplete results, or more annoyingly so, times out.
Or assembling context by hand and created an expensive copy-paste workflow that defeats the purpose of having AI in the first place.

Today we're launching the accurate and exhaustive company search agent you can bring in all your AI tools to truly make them work.

Meet Super MCP.
It gives your AI a dedicated context agent that knows everything your company knows across Slack, Drive, Linear, Notion, Jira, GitHub, and twenty other tools.
→ It answers LLM's each question with real company data
→ It doesn't time out on MCP calls
→ It keeps your context clean
→ It works with Claude, ChatGPT, and Cursor out of the box.

We benchmarked it against real company queries before launching.
Claude with individual MCPs gives 24% perfect answers
Claude with the Super MCP gives 80%+ perfect answers while being 2.6x faster.

Same model. The only variable was the retrieval layer underneath.
Super MCP is live today for all Super users.

Read more about it here: https://www.super.work/mcp

And if you're trying to figure out the context layer for your team, happy to help.

In 2022 we published our compensation formula publicly.
We had 32 people, 25 cities, 9 countries.
4 years later, we removed a big part. Here's what we learned.

1/ Cost of life as the main criteria for our benchmark was idealistic and wrong
Our original model used a cost-of-living as the main index, which essentially answered the question "what does rent cost in Lisbon?".

While it can feel logical to aim for compensation to match the same level of life on multiple locations, it definitely does not feel fair to all, and brought hundreds of issues when negotiating salaries for existing and new teammates.

We switched from looking at cost of living to simply basing our numbers on a benchmark of actual salary data from over 1,000 venture-backed SaaS companies in our locations.

The question became "what do top companies pay a senior engineer in Portugal?" and setting a competitive number from there. Completely different framing.

2/ We kept on simplifying the structure and making it more transparent.
A comp model only works if everyone using it can explain it in 60 seconds. At first, ours couldn't pass that test.

The best way for simplicity is by exposing not only the formula but also the results. We ended up giving our team team a public datalooker sheet with all the levels/countries/roles and associated comp accessible in a few clicks.

3/ We raised our benchmark over and over as we grew, got profitable, kept on growing.
A defining moment came in 2024 when Kamsa data showed that salaries had dropped across the board.

We chose to keep our 2022 benchmarks anyway. Market data should be a guide for doing right by our people, not an excuse to quietly cut costs when the numbers give us permission to.

The rest of our calculator remained, and most of our principles still apply (go check the original piece!)

I'm sharing this because comp deserves more thoughtful attention in startups than it usually gets.

Young founders either overpay early and create expectations they can't sustain, or underpay and lose the people who built the foundation.

Both paths lead to hostile team dynamics that are incredibly hard to undo once they set in.

Youtube can teach you to implement RAG over a weekend.
So why'd we spend 2 years?

RAG is the to-do app for the AI era. 
Every developer will build one as a pet project to learn about LLM implementation. 

There's plenty of free Youtube tutorials, wire up an open source vector store, and get answers.

But that's level 1, it only works for predictable questions.

The moment your team has real questions, and knowledge scattered across Intercom, Notion, Slack, your CRM, and 6 other tools - a single retrieval method breaks down fast.

What we've spent 2 years building at Super is an company search agents, orchestrating dozens of tools and sources, adapting to what it finds and able to search in multiple different ways.

That means:
→ An LLM query planner that decomposes your question, prepare sa first series of steps, selects filters before a single retrieval even fires
→ Multiple retrieval engines running in parallel or in sequence — semantic, keyword, SQL, MCP, and hybrid
→ Permission filtering at runtime so people only see what they're allowed to see
→ Ranking, reranking, and hallucination prevention baked in — not bolted on
→ Every answer cited, verified, and source-linked

Could you build this on n8n? No. The gap between a RAG pipeline that returns chunks and a retrieval agent that thinks about your question, searches intelligently across every tool your team uses, and verifies its own answer - that gap is the product.

We didn't build a wrapper around embeddings. We built the most thoughtful multi-tool retrieval agent we could. And we keep on adding to it.

Your customers can feel the gap between your landing page and your support calls.
That gap is your actual brand.

I don't think SaaS has reached a consensus on what brand actually means.
Everyone uses the word. Very few people mean the same thing by it. Is it your visual identity? Your positioning? Your vibe? The feeling someone gets after using your product for a month?

After 10 years of building companies, here's the working theory I've landed on. 

Brand is the extrapolation of how you actually treat your team, your customers, and what you care about when nobody's evaluating you.

1/ A good brand is downstream of your internal culture and values
At Super and Slite, I've noticed the moments where our brand felt strongest where our tone, our design, our content just happened to match how we actually behave internally.
When your team is warm, playful, and obsessively helpful behind the scenes, and that same energy shows up in your onboarding, your docs, your error messages = something clicks.
People trust it because it's consistent in a way that's hard to fake.

2/ A good brand can't be retrofitted
Where I've seen it go wrong, including in my own work, is when you start from the market. You look at competitors, pick a lane, then backfill a personality.
The illustrations look friendly. The copy sounds human.
But then a customer hops on a call and the energy is completely different.
That gap is hard to recover from.

3/ How I keep operating
Name what's actually true about your company first. How do people talk to each other? What do you default to when things get stressful? Then take that vibe and push it into every touchpoint.

It sounds obvious written down. In practice, almost nobody does it this way because it requires admitting what you actually are before deciding what you want to be.

Still figuring this out honestly. But 10 years in, this framing hasn't let me down yet.

Our median time to close bugs dropped 60% this year.
The obvious assumption is that AI coding tools did it. 
But the actual reason is a bit more subtle, and less exciting than that.

We spent 6 months last year deleting, cleaning and refactoring.
We cut 3 features that had been creating edge cases for years.
We converted everything to TypeScript, and migrated off deprecated BrowserView entirely.
We moved from ESLint to Biome and got our linting time for the entire codebase down from what was effectively infinity to 7 seconds.
We reshaped entire core parts of our codebase.

Just cleanup. That work is what made AI truly effective afterward, and I feel every day that a mature codebase with this level of quality is the unfair advantage startups will die for in the future.

When your codebase is simple, bugs are easier to find, easier to reproduce, and easier to fix, by human and agents alike.

AI coding tools amplify that simplicity because they're working with a clean surface instead of fighting through layers of dead code and undocumented edge cases.

The compounding effect showed up faster than we expected. One of our engineers spent three weeks refactoring Super's core engine with zero visible product changes. After that architectural work, the team added Bigquery as a data source in 4 days, Salesforce in 3, and the next two sources took 2 days each. That refactor felt slow in March. By November it had saved us 8 weeks of work.

PRs merged per contributor went from around 30 per quarter to 70 last year, more than 2x output with the same team and headcount.

The reverse is also worth thinking about. If your foundation is messy, AI tools help you create bugs faster and ship technical debt at a pace that would have been impossible manually. Speed is a multiplier, and it multiplies whatever is already underneath.

Most teams I talk to right now are shipping 2-3x faster with AI coding tools, and that's genuinely exciting.

But I think the conversation about what to do before you go fast is getting skipped entirely. The 6 months we spent cleaning up felt unproductive at the time, but that unglamorous work is what actually moved our metrics.

Iwo Szapar

Hybrid Work Expert

🚀 Remote-First Activist | Top 50 Remote Influencer | Since 2017, shaping the future of remote-first world

Aloha, I'm Iwo Szapar! Over the years, I've helped transform how over 3,000 companies approach work, leading to more efficient and enjoyable professional lives. 🌍

Key Achievements:

▪️Co-created the AI Maturity Index with Harvard researchers, democratizing access to enterprise-grade AI readiness insights
▪️Advised Ministry of Communications and Technology of Saudi Arabia on AI up-skilling for startups
▪️Launched world's first certification program for remote workers: Remote-how Academy, back in 2018.
▪️Established strategic partnerships with 150 companies, including Asana, Deel, Remote, and Safetywing.
▪️Created an expert community of 250+ consultants from companies such as GitLab, Netflix, and Hubspot.
▪️Co-organized 3 editions of Remote Future Summit, reaching over 11,000 attendees and featuring 140 speakers.

Born in Gdansk, Poland, I've embraced the 'slowmad' lifestyle, living in various countries while working remotely. This journey has enriched my perspective and fueled my passion for innovation. When I'm not working, you can find me reading history books, following international affairs, or indulging in my hobbies as a dog lover, amateur surfer, and DJ.

Connect with me to explore how you/your company can work smarter! 🚀

🚀Remote Work Advocate & Co-founder

Remote-how helps companies make remote & hybrid work, work. Since 2017. 

🤓 Remote-how Marketplace - the world’s leading remote & hybrid work experts marketplace. Work on your consulting and advisory projects with 200+ pre-vetted practitioners from top distributed companies. 

🚀 Remote-how Campus - a community where leaders of hybrid teams come to connect, learn and grow together with access to live leadership development programs, mentoring services, and more.

$50k revenue in three months from a side-project. Two other products in the making, while working my half-time job. 

No team. 
No VC. 
No startup story. 

A small, profitable product.

Just me + dozens of AI Agents, and an obsession of going AI-first with 99% of work tasks I do.

IE University's podcast asked what advice I'd give entrepreneurs. My answer surprised them. (I guess...😅 )

Forget the unicorn. 

Build small. 
Build profitable. 
Build alone if you have to.

Skip the unicorn obsession. 

The founders winning right now are the ones running lean, staying profitable, and using AI as their operating layer instead of a headline.

Now advantage goes to whoever moves before the playbook is written - right now, that's the lean operator, not the firm with 500 analysts."

Keep in mind that we're at maybe <5% AI adoption globally. 

Still the first inning. 

The window to figure this out before everyone else does is narrow.

Is the lean founder model genuinely better - or does it only work for certain product types?

Sooo... coming back to the interview: Ainhoa asked great questions, and our conversation went places I didn't plan for.

Enjoy tull episode in the video - link in comments.

Gracias Ainhoa for a super energising chat and Mercedes for the invite ❤️ 

Sending good vibes to my IE / South Summit friends and hope to see you in a few weeks in 🇧🇷 Victoria Juan Christopher Joe Francisco Geoffroy Nacho Liz João Camila Mateo Juan Andrea Emma María Maria Gabriela Fernanda

You read posts about AI every day. That does not put you in the top tier.

0.04% of humans use AI daily to ship real work. 

0.3% pay for any AI tool. 

The rest are observers.

Reading about AI, sharing posts about AI, attending AI workshops: none of that moves you up the distribution. 

Building something does. 

Running a model against your actual work does. 

Getting Claude Code to do a real task in your real environment does.

I deployed Second Brains for 85 people. 

The ones who moved tiers fastest did one thing differently: they stopped consuming AI content and started running experiments inside their own work.

The AI revolution people keep announcing has not happened. 

For 99.96% of people, it has not started.

You already know what to build. 

The gap is not ideas. 

Where do you stand with AI adoption?

Start here: https://lnkd.in/dgqpKJyd

AI Adoption Tiers among knowledge workers 2026 

I cancelled my ChatGPT subscription last year. Now OpenAI sees a mass exodus of users. Why? 

It’s following the deal with the Pentagon over AI military use, where Anthropic rejected the deal due to its firm position on AI ethics. 

The CEO Dario Amodei refused to accept the deal for two reasons: 
- the use of AI for mass surveillance of American citizens
- managing autonomous weapons.

Is this a temporary problem for OpenAI or a part of a bigger trend where they might loose the pole position in the AI labs competiton? 

PS. Have you cancelled your ChatGPT subscription - what was the reason? Have you joined the Claude Code family for good?

Thank you IE University for having me ❤️ Muchas gracias! 🫡

The latest episode of Venture Ahead explores the future of work with Iwo Szapar, an entrepreneur, writer and speaker and the founder of the AI Maturity Index.

From the rise of remote work to a world shaped by automation, augmentation and distinctly human skills, this conversation, recorded during South Summit Madrid, dives into the profound shifts redefining how we work and how we live. As AI agents move from prediction to reality, the question is no longer whether change is coming, but how we adapt to it.

For founders, leaders and professionals navigating this transformation, this episode offers a sharp look at what’s just beginning.

Watch now and #VentureAhead: https://lnkd.in/edN3fx8V

Ainhoa Valencia | Victoria Pérez Jiménez | Juan José Güemes | IE Entrepreneurship & Innovation Center | IE University Lifelong Learning

I built a tool that grades AI Second Brain setups. It gave my own setup a 76% 😅

Everyone assumes the person who builds the grading tool at least passes their own test.

Overall: 80% - Grade A. 

But Setup Quality scored 76%. 

That's a B.

397 out of 499 points across 140 automated checks.

Here's where it got embarrassing:

1. AI Fluency: 93%. Five checks scored perfect. Reference Integrity: 60%. My files point to things that don't exist. Embarrassing when you're the one who wrote the scoring logic. 

2. Setup Quality: 76%. Model Configuration scored 0%. Sandbox scored 13%. I literally skipped the config I tell other people to set up. Progressive Disclosure: 98%. 

3. Self-Correction and Compound Learning: both under 60%. The system I built knows I'm not using half of what it checks for.

The tool placed me at COMPOUNDING - fourth of five levels. 

Not yet Production-Grade. 

Which means there's a ceiling I haven't hit yet.

Three fixes would add 14 points:
- Auto Memory (+5)
- Quality Tracking (+5)
- Growth Log (+4)

Fifteen minutes of work I keep putting off.

The tool is Open Sourced - it's free. 

If you want to be publicly humiliated by your own setup, install it in one line:

claude mcp add second-brain-health -- npx second-brain-health-check

Read more: https://lnkd.in/dqnjpsrd

Full breakdown in the carousel.

What's the one part of your setup you know is broken but keep ignoring? 

Mine was Model Configuration. Scored 0%.

Second Brain Health Check Iwo Szapar 2026

AI tools made my clients productive. Then they asked me to remove every single one.

Not because the tools were bad. 

Because every tool came with the same trade-off: someone else owned the intelligence.

Notion AI? Your data on their servers. 

ChatGPT? Zero memory between sessions. 

CRM automations? Break the moment your workflow changes.

After building 81 Second Brains across 12 industries, the pattern is always the same. 

People start with tools. 
Then they want a system. 
Then they want to own it.

What they actually want is a fourth category that nobody talks about.

A system built to their exact workflow. 

Running on their own infrastructure. 

Vendor-independent. Claude today, GPT tomorrow, Gemini next month. 

You own it. Completely.

The discipline behind this is context engineering: managing what the AI knows, when it knows it, and how that knowledge compounds across sessions.

The industry default is renting intelligence from a vendor. More and more people want to own it instead.

Does that gap feel real to you?

I'm packaging v2.0 in the next 7 days.

Comment below what an ideal Second Brain should do for you 👇

AI is like a box of chocolates. You never know what you're gonna get, but it will absolutely be confident it gave you exactly what you wanted.

taplio

The Battle

Christophe Pasquier

Iwo Szapar

Followers

Posts

Engagements

Likes

Performance ScoreChristophe Pasquier's LinkedIn Performance

Performance ScoreIwo Szapar's LinkedIn Performance

Ready to grow your LinkedIn presence?

taplio

The Battle

Christophe Pasquier

Iwo Szapar

Followers

Posts

Engagements

Likes

Performance Score.css-goub6s{font-size:var(--chakra-fontSizes-md);font-weight:500;color:var(--chakra-colors-gray-600);display:block;margin-top:var(--chakra-space-1);}Christophe Pasquier's LinkedIn Performance

Performance ScoreIwo Szapar's LinkedIn Performance

Ready to grow your LinkedIn presence?

Performance ScoreChristophe Pasquier's LinkedIn Performance