The single biggest problem in communication is the illusion that it has taken place.

George Bernard Shaw

Why a Framework?

The single most important thing that we do at work is communicating with other people. It’s generally how we are able to come up with ideas and execute them in ways that a single person could not.

It does seem that this whole “talking to each other” thing can get complicated. “Miscommunication” seems to be the number one excuse for something getting messed up in a knowledge worker environment. There are a whole host of reasons why this is the case. But one of the easiest ways to combat the lack of retention, the lack of comprehension, or simple miscommunications is to start with the way that we express ourselves.

At Sourcetoad, we use an adapted communications framework that has made life a lot easier for everyone involved. We have set up some basic rules for communication that are easy to remember, and we use keywords so that people receiving the information can context switch into the receiving framework mode. In other words, when people incite the framework, everyone changes their mental stance and prepares to communicate.

An Adapted Simple Model

This framework has been adapted from an amalgamation of numerous other frameworks. It takes a lot from military communication tactics (where being understood can be the difference between life and death) and a number of other popular communication frameworks. This is just the simplest way that we’ve been able to express it. It has been hacked together from too many sources to cite, but it is still simple enough to work well for us.

The Framework

Our framework has only four key pieces:

  • Intent
  • Context
  • A sketch of the desired outcome
  • A sketch of a strategy to get to that outcome

These four items can be placed in various orders, but typically they start with intent and end with a strategy.

Intent

Stating your intent, or at least clearly knowing what your intent is, is the most powerful part of this framework. Understanding your own intent in everything is extremely powerful, but that’s another blog post. Conversations that do not have a well-understood intent are just “chats.” They’re not the type of communication that will solve any problem.

Stating your intent at the beginning of a conversation does two very important things:

  1. It switches the receiver’s brain into “communications framework mode.” It allows the other person to understand that you are about to use the framework.
  2. Stating your intent allows the person to whom you are speaking with to know why you are talking. If I don’t know what you want right at the beginning, we’re probably not going to have a fruitful conversation.

Context

Context is the backstory or history that your receiver may need to fully understand the conversation. Telling the person you’re talking to about the players involved, what previous conversations touched on, or what the stakes are can be extremely useful.

The three main questions you should ask yourself when giving context are:

  • What are we talking about?
  • What do you need to know about this?
  • Have I told you everything you need to know?

When saying this bit out loud, you can use the following trigger phrases to make sure your receiver knows you are using the framework:

  • “For a little background…”
  • “For context…”

Sketch Desired Outcome (End State)

After you’ve laid out your intentions and the context the receiver needs, it’s time to actually tell them what you want. This involves explaining your vision of the outcomes, or the “end state.”

An outcome or end state might be as complicated as: “I think what I want is for the company to open a new line of business, complete with staff and warehousing. I also think we’re going to need to custom build an entire logistics software system over the next few years.”

Or it could be as simple as: “What I would like is that at the end of this conversation, we set up a time to have a formal meeting about it with the team.”

You need to be flexible here because even though you might know what type of outcome you are looking for, you need to leave room for the solution to include new ideas from your audience. That’s why we call it a “sketch.”

When saying this bit out loud, you can use the following trigger phrases to make sure the receiver can envision what you want to happen:

  • “What I see happening…”
  • “My desired outcome is…”

Sketch a Strategy

You know what you want (intent), the receiver knows what you want (end state), and they have the backstory (context) to understand what you’re talking about — we can now move on to action.

In this phase, we outline a possible method of getting to that end state I mentioned earlier. This is up for discussion, of course. The person you’re speaking with is not required to follow your sketch. Rather, this phase invites them to build a strategy with you to accomplish the desired outcome.

The person you’re speaking with might have a much better idea of how to get there than you do, especially since they now understand your intentions and what the end goal is. So keep an open mind, and enjoy the brainstorming.

When describing the strategy you envision, Use triggers like:

  • “A rough strategy we could take is…”
  • “A path I see is…”
  • “I’d suggest x as the next steps. What do you think?”

Example 1

Intention: I want a dashboard to show the ten most important KPIs for our internal product. I want the team to manage the build-out and timing to balance client needs. I’m prepared to invest about 100 hours for the MVP.

Context: Hi Joe, some quick context: I would like for the team to build a dashboard that provides a brief overview of the system – I want this to show the variety of features for sales calls and to be useful for current clients.

Outcome: My desired end state is I get a demo-able dashboard on our test instance within the next four months. It should have 70% of the functionality shown in the mockups.

Strategy: I think the rough path to getting there is for you and Jane to meet and work out which features are doable in the next four months while balancing client requests. Then you can create tickets for the segments and decide how flexible the dashboard could be. Let’s get together for a review and approval meeting when that’s done. After that, we can start handing out the tickets to the team.

Example 2

Intention: I want to get James to switch the DNS servers for a client.

Context: Hey James, for some context, Martin asked me to help him with their new mail server. They’re going to be setting this up on their side with Office365. I’m not sure what is required 100%, though.

Outcome: I would like to send Martin an email with the steps he needs to take to prepare for the switchover and the dates when we plan on doing it. If we have any questions for him, I’d like to include those in the email by the end of the day tomorrow.

Strategy: My strategy here is that I will follow your advice and guidance to the letter because I’m not the expert.

Recap

If you are talking to someone at work, they might not actually be paying attention. Having a communications framework with key phrases and trigger words can make a huge impact on changing the mindset of the sender and the receiver. When both parties know that information is going to be transmitted in a certain way, retention and accuracy rates are way higher.

At Sourcetoad, we use the trigger words and key phrases below to help change our thinking, speaking, and listening modes:

  • Intent
    • “My intention is…”
    • “What I’m looking to do is…”
    • “What I want is…”
  • Context
    • “For some context…”
    • “A little background…”
  • Sketch of my desired outcome
    • “The outcome I’m looking for is…”
    • “When this is all done, I’d like to see…”
  • Sketch of a strategy to get there
    • “I think a rough path to get here is…”
    • “The strategy I imagine is…”

That’s it! It’s a very simple yet powerful tool to help improve communication. You can alter this plan or invent your own, but the key is that both parties know the rules. The idea that people can switch between a conversation and “communication” is life-changing – but it requires training on both sides.

Previous ArticleNext Article
I help companies turn their technical ideas into reality.

CEO @Sourcetoad and @OnDeck

Founder of Thankscrate and Data and Sons

Author of Herding Cats and Coders

Fan of judo, squash, whiskey, aggressive inline, and temperamental British sports cars.

Leave a Reply

Image generation comparison from February 2026

I spend a lot of time generating images these days for presentations. My typical workflow is fairly scientific: I ask Midjourney to produce a relatively cute image of a frog, a toad, a robot, or some other vaguely anthropomorphic creature doing something related to the slide I’m about to present.

Once I get the image, I expand the background by about 90% so the character ends up in the corner of the slide. That gives me a nice, relatively clean area to drop text on top. Sometimes I use Photoshop to do the expansion. Sometimes Midjourney cooperates. ChatGPT is actually pretty good at this too. Nano Banana is… enthusiastic. It tends to try a little too hard right now.

That’s fun and all. But the more interesting comparison isn’t cute amphibians. It’s boring enterprise diagrams.

Recently I had to generate some architecture visuals for an RFP response. Rather than suffer alone, I decided to turn it into a model comparison experiment.

Below is a slightly simplified (but very real-feeling) prompt I used. The company is fictional. The buzzwords are not:

Create a clean, executive-level architecture diagram titled “Closed-Loop Member Intelligence Platform.”

The layout should be 16:9 and structured left to right with a circular optimization loop surrounding the system.

On the left side, show multiple member touchpoints feeding into the platform:
- Website (class browsing, account login)
- Mobile App (workout tracking, push notifications)
- In-Club Kiosks (check-in terminals)
- Wearable Device Integrations (fitness trackers)

Label this section: “Member Interactions Across Digital & Physical Channels.”

All touchpoints should flow into a large central hub labeled:

“Unified Member Profile & Real-Time Event Engine”

Inside the central hub, include:

- Web SDK
- Mobile SDK
- API Gateway
- Event Streaming Layer
- Clickstream Data Capture
- CRM Data Sync
- Identity Resolution Engine

Include a small sub-caption:
“Event-level data unifies anonymous visitors and active members into a single dynamic profile.”

From the central hub, arrows should flow to a right-side activation layer labeled:

“Real-Time Engagement & Orchestration”

Include these outputs:

- Personalized Workout Recommendations
- Dynamic Class Availability Messaging
- Triggered Retention Offers
- Membership Upgrade Campaigns
- A/B Testing & Experimentation Engine

Surround the entire diagram with a circular arrow labeled:

“Continuous Optimization & Revenue Growth”

Along the circular loop, include metrics:

- Engagement
- Conversion
- Retention
- Lifetime Value

Design style should be modern, minimal, and suitable for an enterprise SaaS presentation.
Use neutral tones with one accent color to indicate data flow.
Avoid clutter.
Make the architecture clear and readable for both technical and executive audiences.

Here are the results.

ChatGPT

Clear winner for “looks like a human consultant made this at 11:30 p.m. before a board meeting.” The text was incredibly legible. The layout was balanced. The hierarchy made sense. It genuinely looked like something you’d expect in a mid-market SaaS pitch deck.

I even did a reverse image search on some of the icons. No exact matches. That suggests they were generated rather than assembled from some common icon pack. Which is pretty cool.

Claude

Claude did something interesting. Instead of just giving me a static diagram, it generated a React application that rendered the architecture visually inside its canvas. I should have guessed this is what that nerd would do… in fact I did guess, but whatever.

That has upsides. I can tweak the code. I can modify the layout. I can version control it. That’s appealing to the nerd in me.

But technically it failed the homework assignent. It wasn’t what I asked for. I asked for a diagram image. What I got was a React app that displayed a diagram that I had to screenshot.

That said, I actually liked the aesthetic. It felt a little more “me.” Slightly less textbook. Slightly more product-thinking.

Gemini (Nano Banana)

The undisputed champion of 2026 in image generation, nano banana, was actually my least favorite of all of the designs. I think there’s something really weird about the arrows on the outside ring of this diagram. Why are there two arrows between “Engagement” and “Conversion”? Why are they different sizes? I did actually find a couple of exact matches when searching for some of these icons here, so so there might be some assembly on top of generation going here, but I cannot tell because these icons are so universal that it’s likely that that could just be a coincidence.

Midjourney

Ah, Midjourney. My current favorite for keynote frogs.

Completely and utterly useless for generating readable diagrams.

It’s phenomenal at stylized imagery. I’ve tuned it so much over time that it practically knows my aesthetic preferences better than I do. It’s like it’s been trained specifically to make amphibians that align with my personality.

The Omni feature (object permanence) is genuinely impressive. If you’re telling a visual story and need a character to look consistent across multiple scenes, or you’re creating a children’s book to convince your six-year-old that haircuts are not a violation of human rights, it’s fantastic.

But enterprise architecture diagrams? Nope, sucksville.

Wrapping Up

I was pretty sure that nano banana was going to run away with this one. Everyone I know works in banking or finance or medicine has been telling me how great the model is for generating diagrams and process flows. They’ve been raving about how things that were not possible three months ago are now completely durable with this model. It was a little bit of a surprise to see that my personal favorite was good old-fashioned ChatGPT. I think, for my personal use, I’m probably going to use Claude to generate diagrams because they’re a lot easier for me to tweak once they’ve been generated.

That said, I think this experiment showed that when I do this kind of work in the future, I’m just going to load up the same prompt in three different models and just pick the one I like the most. Some of it’s going to be personal tastes; some of it’s going to be how well the model interpreted the prompt, and some of it’s going to be the state of that particular LLM and its model on that given week.

And I’m going to stick to only using Midjourney for generating cute pictures of toads.