Powerful but general
AI models are trained on vast amounts of the world's information. That makes them powerful, but general. Out of the box they don't know much about your business or your people.
Dottie understandsyou
Your projects, your people, your language.
How Dottie uses AI
The new stack
The business stack of the future has three layers. Traditional software to hold your data. A horizontal layer that puts AI in your team's hands for individual tasks like emails, notes, and document analysis. And vertical tools that run AI workflows built for specific tasks.
The productivity gap
Many firms have reached the horizontal layer, integrating an LLM into their file management system. Copilot paired with SharePoint is a popular example. This puts AI in their people's hands, but the productivity benefits prove modest. The real gains come from the vertical layer, where workflows are built for specific, high value tasks within the organisation.
Enter the agent
Until recently, AI could answer questions but could not do the work. That has changed. Give an LLM the right instructions and tools, and it can carry a task from start to finish. This is where real ROI lives, but only when the workflow is built well.
The hard way
You could build these workflows in house, but it's fiddly and often rests on one keen staffer who might leave. You could hire a consultant, but they hand over a workflow frozen in time, leaving you with the maintenance burden. Some workflows will be built and maintained in house, but not everything. The critical ones, like bid drafting, need to be done right.
A dedicated system
Dottie is a specialised AI tool for bid drafting. Proven workflows, real quality control, and genuinely easy to use. For around $50 a proposal you get a repeatable, reliable, collaborative assistant for your firm's proposal writing. The ROI is simple: save one hour of a director's time, or win one extra job this year, and it has paid for itself.
What Dottie does
Giving AI access to your information isn't enough.
It needs to know what information it has available and how to use it.
Dottie categorises your knowledge
AI reads and categorises every document you upload, building you a curated knowledge base enriched with intelligent metadata.
Then it retrieves what's relevant
For each task, Dottie searches this curated knowledge base and pulls in the documents and instructions that matter for effective proposal drafting.
And knows how to use it
Expert prompts tell Dottie how to use each piece of retrieved information, leveraging the intelligent metadata. This ensures your knowledge is applied the right way, every time.
The result is not a generic model with your files attached, but an assistant that reflects your experience, knows your team, and writes the way your firm writes.
See for yourself below
Dottie vs
ChatGPT
We ran three AI workflows across multiple firms, each producing a draft proposal section.
The chart shows the average similarity of these drafts to real submitted proposal sections.
The higher the score, the less editing between AI draft and final.
Average benchmark scores: RFP plus simple prompt 34 percent, RFP plus past proposal plus simple prompt 35 percent, and Dottie 62 percent. The real submitted proposal section is 100 percent.
Method
We tested three AI drafting approaches against real proposal sections previously submitted by each organisation.
- A simple prompt and the tender documents. The most basic AI drafting workflow.
- The same simple prompt and tender documents, plus one example of how the organisation has responded to similar work before. More context, but no guidance on how to use it.
- Dottie, which uses a broader organisational knowledge bank combined with sophisticated prompts. This is designed to produce a draft that is closer to how the organisation actually writes.
Each output was scored against the real human-written section that was actually submitted. The score measures two things:
- Semantic similarity: whether the draft is talking about the same ideas as the real proposal.
- Structural similarity: whether the draft has the same shape, depth and length as the real proposal.
We weight structure slightly more heavily, because a draft that's the right length and format is faster to edit into something usable.
The benchmark isn't trying to prove AI can replace a proposal writer. It can't. It's measuring how much editing effort each approach is likely to leave behind.
Security without complexity.
Dottie uses Microsoft Azure and Azure OpenAI, the same trusted AI foundations as Copilot.
Nothing you put into Dottie can ever benefit another organisation, nor is it used to train general AI models.
We take your information security seriously.
| Part of the stack | How Dottie handles it |
|---|---|
| User authentication | Your account is protected through Microsoft's secure sign-in platform. |
| Data storage | Your documents and project data are stored in Microsoft data centres in Australia. |
| Data transfer | Your data is encrypted in transit and at rest, using Microsoft's enterprise-grade security standards. |
| AI processing | Handled through Azure OpenAI on Microsoft's secure global network. |
| Data isolation | Data is isolated using industry best practice row-level security policies. |
| AI model training | Your data is never used to train the underlying AI models. Microsoft strongly commits to this here ↗. |