Generative AI is getting better every day. We now have ChatGPT4, Claude 3, Gemini, Perplexity, and whole gamut of specialized GenAI tools that await your discovery. And people are using these tools in creative ways.
For example, UNICEF now explicitly states that they will not accept job applications that use Generative AI. I wonder how they would know when 70% of job applicants use GenAI today. Maybe if the application was an obvious copy/paste or careless applicants included “as of my last knowledge update” in their documentation. In that case, the application should be trashed because it’s a bad application, not because the applicant used GenAI.
Which brings me to today’s question: “Should it matter if a proposal is written using Generative AI?”
How Is Generative AI Different?
We are already using different types of AI to write everyday correspondence. I know you used AI in your proposal process, even if you didn’t think of it as artificial intelligence. For example:
- Autocomplete is a simple AI automation program.
- Spellcheck and Grammar Check are pattern recognition AI.
- Google Translate is AI interpretation.
Generative AI is using probabilistic algorithms – a fancy way of saying it guesses at the next most common associated word or phrase, versus “knowing” anything – to create plausible text that may or may not be based on a known reality. It still takes human cognition to understand if the text is factually correct and edit it to make sense in the context of the full document.
3 Ways GenAI Can Improve Proposal Writing
I liken Generative AI in proposal writing as using a good assistant. It can help, but it’s not going to generate a perfect proposal for you on the first try. At least, not yet. I see three ways that we can use GenAI in the proposal process today. I’m sure you can think of more – add them in the comments!
1. Understanding Requests for Proposals
I already use the Ask Your PDF Research Assistant custom ChatGPT tool to summarize long documents and highlight key themes. This is especially useful when reports don’t have a strong executive summary.
Most donor RFPs have many pages of rules and regulations that crowd around a few select pages of technical explanations of what the donor really wants. I remember a USAID RFP that was 175 pages long, with only 12 pages detailing what was to be done. GenAI tools can cut through the clutter and pull out specific action items.
2. Developing Strong Win Themes
Once you know what you want to do, GenAI can build on proven responses – both from within an organization’s past experiences and from the greater corpus of development knowledge.
For example, DevelopMetrics has created DELLM, a GenAi tools that makes the Development Clearinghouse Exchange useful. It uses DEC entries, tagged and coded by development experts, to find which interventions were the most effective in different sectors and countries. That’s beyond the ability of any single human, but GenAI can do it easy-peasy.
3. Writing Compliant Submissions
I do feel sorry for local organizations trying to compete with traditional implementing partners. The 15 pages of certifications and representations required in many RFPs can be overwhelming even for me – and I’m a US citizen, Native American English speaker, and have 20+ years experience reading bureaucratic forms.
There is no way a 20-person NGO with 10 years of deep local connections that USAID wants, can ever hope to submit a compliant proposal when English is the 2nd or 3rd language learned – unless they use GenAI. That’s one reason I created the ADAIR and ADS Bots, tested GenAI on the FAR, and I am building a FAM/FAH Bot. We need more and better tools for local firms if we’re ever going to increase localization.
If you think GenAI isn’t ready to write proposals yet, then check out Grant Assistant – an LLM designed specifically to co-create proposals with human editors that include strong objectives, complaint activities, and buzzword usage that will be indistinguishable from (or better than) proposals solely written by humans.
What Are Generative AI Downsides?
Fake Quality: A good proposal put through Generative AI tools can become a great proposal, even a winning proposal. Hence, there is a risk that a subpar proposer could use GenAI tools to win a contract and then be unable to implement a successful project in compliance with the donors regulations.
How would that be any different from a subpar organization hiring a great proposal writer to create a winning proposal? Or donors not doing enough due diligence before awarding funding?
Overwhelming Volume: GenAI tools also make it easier to create proposals, allowing more organizations to submit more proposals using the same resources. Hence there is a risk that donors could be overwhelmed by too many quality proposals to judge properly under existing grading schema.
Might that really say that donors should have better RFPs? Or have different submission and grading criteria? Or just use GenAI themsevles to make proposal assessment easier?
Of course this all portends a day when machines will write proposals for other machines to review and reward – kinda like product review sites and Google Search today.
This is a 100% handcrafted post. Though how would you know if I used GenAI in its production – or not?
Nice post, but it assumes that so-called “native” English speakers are proficient in writing English. Many individuals labeled as non-native English speakers, whose parents received a good education, start speaking English from an early age. Therefore, we shouldn’t excessively glorify ‘native’ English speakers simply because they were born in Europe or North America. We encounter their poor English, grammar, and typos regularly throughout the workweek..
It’s becoming frustrating to encounter grant proposal portals that disable copy-paste and include a misguided “AI detector” that rejects text assumed to be generated by AI. Fortunately, this practice isn’t widespread yet but could become more common in the future
Ugh. RFPs that disable copy/paste are horrible for everyone, especially when your well-crafted entry is lost in the submission portal. They also discriminate against those (like me) who need spellcheck to be legible, even as a “native” American English speaker.
Many thanks for making this topic “float”. Many COs are ignoring (on purpose) the possibility of receiving AI-facilitated proposals. I acknowledge that a proposal written by a technical writer can be no different from an AI-generate one. However, the fake promises of either is questionable and unethical. The caveat here is that AI will allow more and more fake and unachievable commitments by the bidders. Oral presentations could be added to the evaluation process (as many university teacher are doing right now)
I am a huge fan of oral presentations. Not only are they easier to create than written proposals, they usually showcase the expected Chief of Party, their interactions with the prospective team, and their leadership capabilities and style – all of which matter immensely when interacting with government leaders. Bonus: oral presentations are graded the same day, meaning all proposals could be evaluated in a week and drastically shortening the overall procurement process.
Using generative AI for writing sentences and creating proposals is a great idea because the more we interact with AI, the more we learn. Allowing AI to assist in our activities is also beneficial.
Why do we assume that we should receive applications and proposals in the same way? An AI tool elongates bullet points into long from writing so that an application/proposal can seem well thought out… eloquent. Perhaps our way of receiving proposals is already deeply flawed and relies too much on a good drafter rather than on substance and easily understood linkages…
Exhibit A “The draft proposal to USAID to deliver plenty of goats…”
– ABC Corporation will deliver hundreds of goats to USAID.
– These are the best goats in the world. They are a famous Italian variety.
– Goats are very useful.
– Goats will positively change the trajectory of a developing agricultural sector.
Exhibit B – Run Exhibit A through OpenAI ChatGPT 4.0 (Note that it took me less than 10 minutes to draft this email and to achieve this product…)
“Me: I am writing a proposal to USAID as a prospective contractor. I am responding to a USAID solicitation posted on SAM.gov. The contract will be a cost plus fixed fee contract estimated at 10 million dollars and will help a fictitious country named Kurblakistania. Draft a 500 word proposal that expands on these deliverables and how great my company will be at delivering them. Feel free to embellish and use outside information that would make this proposal the best! The deliverables: 1. ABC Corporation will deliver hundreds of goats to USAID.
2. These are the best goats in the world. They are a famous Italian variety.
3. Goats are very useful.
4. Goats will positively change the trajectory of a developing agricultural sector.
GPT: Executive Summary:
ABC Corporation is excited to present this proposal in response to the USAID solicitation for the development of the agricultural sector in Kurblakistania. With a rich history in agricultural innovation and a strong commitment to sustainable development, ABC Corporation proposes a transformative project: The Superior Goat Initiative. This initiative aims to leverage the exceptional qualities of renowned Italian goat breeds to revitalize Kurblakistania’s agricultural landscape, ensuring food security, economic growth, and environmental sustainability.
Project Overview:
The Superior Goat Initiative by ABC Corporation is a carefully designed program to introduce hundreds of the world’s finest goats to the rural communities of Kurblakistania. Our project is centered on the famous Italian breeds known for their resilience, productivity, and adaptability. These goats are not just animals; they are the carriers of change, prosperity, and hope for thousands.
Deliverables:
Introduction of World-Class Goats: ABC Corporation commits to delivering hundreds of goats, specifically chosen from the best Italian varieties. These goats are renowned for their high yield of milk, cheese production capability, and adaptability to various climatic conditions, making them an ideal choice for enhancing Kurblakistania’s agricultural productivity.
Superior Genetics: Our selection includes breeds such as the Saanen, Alpine, and Nubian, each known for their exceptional qualities. From high milk production to disease resistance, these goats will set a new standard in livestock farming in Kurblakistania, promoting genetic diversity and improving local breeds through crossbreeding programs.
Capacity Building and Education: Recognizing the importance of knowledge transfer, ABC Corporation will implement comprehensive training programs for local farmers. These will cover best practices in goat breeding, health management, sustainable farming, and product marketing, ensuring that the benefits of this project extend far beyond the initial delivery.
Sustainable Agricultural Development: By integrating these world-class goats into Kurblakistania’s agricultural sector, ABC Corporation aims to catalyze a significant shift towards sustainable and profitable farming practices. This initiative will not only boost the local economy through increased production of high-quality dairy products but also contribute to environmental conservation through natural grazing, soil fertility improvement, and reduced reliance on chemical fertilizers.
Implementation Plan:
Our approach includes a phased rollout, beginning with pilot programs in select communities to optimize breeding practices and training modules. Following the successful integration of these goats into the local ecosystem, we will expand our efforts, ensuring widespread access to these resources across Kurblakistania.
Why ABC Corporation?
With decades of experience in agricultural development projects worldwide, ABC Corporation possesses the expertise, resources, and passion required to make the Superior Goat Initiative a resounding success. Our team of veterinarians, agronomists, and sustainability experts are committed to working closely with USAID and the people of Kurblakistania to achieve lasting impact.
Conclusion:
ABC Corporation’s proposal for the Superior Goat Initiative represents an unprecedented opportunity to transform Kurblakistania’s agricultural sector. By introducing the world’s best goats to this beautiful country, we aim to enhance food security, elevate economic conditions, and pave the way for a sustainable agricultural future. We are excited about the prospect of partnering with USAID on this journey towards prosperity and resilience in Kurblakistania.”
An idea… Reduce proposal page counts… I just ran the same thing in GPT, but had it reduce the word count by 50%. It is actually more clear and concise this way. AI can be used to make proposals more direct and word efficient, making it easier on a TEC / SC and reducing the bias towards well-written documents…
“User: That’s great. Can you turn the proposal into bullet points in under 250 words?
GPT: ABC Corporation is excited to propose the Superior Goat Initiative in response to USAID’s solicitation, focusing on revitalizing Kurblakistania’s agricultural sector through the introduction of premium Italian goats. This initiative is designed to leverage ABC Corporation’s extensive experience in agricultural development, promising transformative impacts on local farming practices, food security, and economic stability.
Key Highlights of the Proposal:
Introduction of High-Quality Goats: Supplying hundreds of renowned Italian goats, specifically selected for their superior genetic traits, including the Saanen, Alpine, and Nubian breeds, known for high milk production, resilience, and adaptability to varying environmental conditions.
Comprehensive Farmer Training Programs: Offering extensive training and capacity-building for Kurblakistanian farmers on advanced goat breeding techniques, health and nutrition management, sustainable agricultural practices, and effective marketing strategies for dairy products.
Sustainable Agricultural Development: Aiming to catalyze a shift towards more sustainable and profitable farming practices. The project focuses on enhancing biodiversity, improving soil fertility through natural grazing patterns, and reducing dependency on chemical inputs.
Economic Growth and Food Security: By significantly boosting dairy production, the initiative promises to elevate local economies, create employment opportunities, and improve food security. The introduction of high-value dairy products into the market is expected to increase farmers’ incomes and provide nutritional benefits to the community.
Environmental Benefits: Promoting environmental stewardship through sustainable farming practices that align with global standards for conservation and biodiversity.
Strategic Implementation Plan: ABC Corporation proposes a phased implementation strategy, starting with pilot programs to fine-tune the project approach, followed by a broader rollout to ensure widespread benefits across Kurblakistania.
ABC Corporation’s proposal for the Superior Goat Initiative outlines a strategic, impactful approach to modernizing agriculture in Kurblakistania, leveraging world-class livestock genetics, expert knowledge transfer, and sustainable practices to ensure long-term success and resilience.”
Happy exploring!
Bryan
You are making a number of unsubstantiated nuances that AI will level the playing ground for non-native english speakers. I wasn’t aware that proposals written by non-native speakers had a higher failure rate and was an important indicator to factor in. That aside, everything being equal, I would think that in-country experiences and relationships built over time while implementing successful programs would actually give you more of an edge.
The language skills in the proposal can be used to infer the skills and ability of the proposing organization. I personally do not agree with this judgement, but it is one that is sometimes employed by donors as they review applications.
Optimistic post. And yes, while Gen AI greatly helps local NGOs, they are still likely to be exposed to the better part. Hope literacy on this will work the rest.
The last sentence is appreciated
What if AI is being used to evaluate AI written proposals? Like many of us, will AI have a bias towards itself?
As someone with an admittedly strong bias on this topic, I believe proposals should primarily focus on effectively communicating good ideas and capabilities, along with highlighting past performance and partnerships. It’s unfortunate that many organizations struggle with archaic requirements, such as not having the exact business language proficiency demanded by donors, even though most of these organizations prioritize localization. This presents a significant barrier to entry for many organizations, especially those operating in countries where the majority of these programs are implemented.
Speaking from personal experience as the leader of such an organization, and as someone with dyslexia, I have always had confidence in my ideas and our capacity to deliver. However, I would consistently face challenges and waste valuable time navigating the intricate details of preparing a proposal. It wasn’t until I started using Grammarly that the quality of my proposals drastically improved, simply by fixing and professionalizing my language. AI-powered assistance is a natural evolution and could level the playing field, enabling these organizations to showcase their strengths and innovative ideas.