Is it believed that all UV completions have "Maldacena duals"? I have heard occasional rumors that effective field theories have gravity duals.  For example, I've been told that UV momentum cutoffs in N=4 SYM become finite radii in AdS.  I've heard speculations about AdS duals of plain old QCD.  And I know it's thought that CFTs always have gravity duals.
Is it believed that any UV completion of an effective field theory must have a Maldacena-style gravity dual (in Witten's sense, meaning that currents become boundary conditions)?  Can QFTs with gravitational sectors have gravity duals?   What about string theory?
Are there any necessary reasonableness conditions?  (Maybe insist that the renormalization flow is a gradient flow?)   Is locality necessary?   (String theory seems to think that gravity must be holographic.  Can you have a holographic description of a holographic description?)  
 A: Maldacena duality, or AdS/CFT is a duality between conformal field theories(without gravity) in flat space and quantum gravity in an asymptotically AdS spacetime of one higher spatial dimension. Quantum gravity has many possible phases. For example, there is a limit of quantum gravity where things look like classical gravity with small quantum corrections(semiclassical limit). Another phase is the tensionless limit of string theory(where strings are infinitely easy to excite): this phase does not look anything like classical gravity and is highly stringy. These phases correspond to different phases of the boundary conformal field theory. So if your question is what are necessary conditions for the boundary CFT to have a semiclassical gravity dual, the answer seems to be CFTs with a large N species of field transforming under some gauge or global symmetry group(e.g. SU(N)) that have a sparse spectrum of operators under any fixed energy. This idea was originally put into test here: https://arxiv.org/abs/0907.0151 I'm not sure if this is the question you are asking though. If it is, let me know and I will elaborate on this.
