Pitch
Create slides that win
4.5•38 reviews•2.6K followers
Create slides that win
4.5•38 reviews•2.6K followers
Pitch is the AI presentation workspace where professionals collaborate on, create, and deliver winning slide decks — all while staying on brand. Whether you’re in tech, media, or the creative space, AI-powered features and collaborative workflows help teams craft consistently high-quality slides in minutes. And with digital sales rooms, engagement analytics, and integrations, you can impress clients and close with confidence.
This is the 11th launch from Pitch. View more
Pitch Agent
Launched this week
Most AI tools apply your colors to generic layouts and call it “on brand.” Pitch Agent builds from your template, design language, and image style. Generate slides from a prompt and file attachments, then refine them via chat. Agent lives inside Pitch, the workspace where teams collaborate on and deliver presentations.
Free Options
Launch Team
Isn’t it possible to just point to a website and take the style from there?
Pitch
@natalia_iankovych Pitch Agent comes with a branded template generator pulls brand data from your domain. Is that what you were imagining or would you prefer to just add the domain as part of the prompt?
@maresch Yes, that's what I asked. Thank you!
This is one of the more natural places for AI in a creative tool because “on brand” is such a context problem, not just a generation problem. The hard part is usually not producing a deck-shaped object; it is knowing which prior slides, customer language, visual rules, and internal shorthand are allowed to influence this specific deck.
I’d be curious how Pitch Agent handles conflicting context. For example, if the brand kit says one thing, a recent sales deck says another, and the user asks for a third direction, do you expose any “I used this because…” trail so the team can trust and correct the output?
@jim_jeffers I think the conflicting-context case is real, but the "I used this because…" trail might be asking the tool for something it isn't really built to hand back. The reasoning an LLM returns isn't a recording of why it chose A over B. It's another generation produced after the fact, the same way the slide was. Run it again and you'll get a slightly different story.
The mental model I've landed on: it's closer to an unobserved field than a decision engine, and your prompt is the thing that collapses it into one specific output. Point three conflicting contexts at it and you're not getting a wrong answer, you're getting whichever one your input happened to pull out this time.
So the leverage isn't "make the model explain itself," it's what you feed it. Concretely: state the tie-breaks up front. Brand kit beats last quarter's deck, the new ask beats both, whatever your rule is. Rather than auditing the decision afterward, you resolve the conflict before it ever generates. The template-as-source-of-truth design is already half of that, it kills a bunch of competing readings before generation even starts.
Wrote the longer version of this idea here if it's useful: https://dev.to/whetlan/ai-who-i-am-and-what-im-supposed-to-be-in-the-software-world-1e8d
"Look like your team made it, then refine via chat without leaving the editor" — this is exactly the bar that makes AI deck generators worth using vs. a thin wrapper. I run a finance YouTube channel (Mod3Loop, https://www.youtube.com/@Mod3Loop) where every video script eventually becomes a slide visualisation problem, and the gap between "AI-generated boilerplate" and "this could actually go in front of an investment committee" is huge. Real test for me: can it produce a slide that defends the same number the same way the model defends it (so the deck and the workbook never drift)? Curious whether Pitch Agent can ingest a finance model and produce a deck whose numbers are sourced rather than re-stated by the LLM.
Pitch
@samir_asadov fascinating use case! Currently the closest thing Pitch Agent offers is attaching a CSV to a prompt. When you say “sourced” do you imagine a citation back to a cell? Live link? Or something else?
Cell citation is the higher-leverage of the two for me. The case I care about: a number in the deck (say, Y3 EBITDA margin) clicks through to row 47 of the model, so when someone in the meeting asks 'where does 18% come from' you can defend it without re-opening Excel side-by-side. Live link is the dream for working models being refined in real time, but cell-level citation is what makes a deck audit-ready — and that's the bar IC decks actually need. The combo would be transformative.
Pitch
@samir_asadov thanks for the extra context, that gives us a really clear picture. Going to bring this back to the team.
Pitch
I just one-shotted a PH launch deck using this prompt:
Pitch Agent perfectly incorporated our messaging (pasted it from Notion) and included the product images I attached to the prompt 😎
@maresch This is really impressive. 👍
Kilo Code
@maresch stunning - what's the AI model you're using under the hood?
Pitch
@fmerian currently using @Claude by Anthropic Opus 4.5 as the default, Haiku 4.6 as a sub-agent for predictable tasks, and GPT 5.4 as an option for the faster mode. For images: Nano Banana 2 and some custom models for specific tasks. We’ll keep evaluating models to always use the best ones to get the job done
So proud of the team and all their work building Pitch Agent. It's been so cool watching it grow in our weekly demo sessions, and now to have it in the hands of our users! My favourite feature is being able to plan and test your storytelling through the Agent chat - it's like having a little presentation sidekick right there with you. Plus, shoutout to the new templates that went live with this launch! Gorgeous!
Kilo Code
@emmasurayadoyle Pitch's presentation templates (launched here in 2021 and Top Product of the Week btw) have always been a source of inspiration for me - any new templates you'd recommend to start with?
@fmerian The 'Bloom' template, for sure! The styling on the images in there is super nice and it's got some really versatile layouts.
The jab at "apply your colors to generic layouts and call it on brand" lands because that's exactly what most of these tools quietly do. Building from the actual design language and image style is a much harder promise to keep — the real test is whether it respects the weird, opinionated stuff in a template, not just the color tokens.